Center positioning method and device of fluorescent cluster, terminal equipment and storage medium

Abstract

The application discloses a center positioning method and device of a fluorescent cluster, a terminal device and a computer readable storage medium. A preset clustering algorithm is used to obtain a brightness segmentation threshold of a sub-image of a fluorescent image. The sub-image is subjected to threshold segmentation according to the brightness segmentation threshold to obtain a fluorescent cluster segmentation image corresponding to the fluorescent image. A fluorescent cluster template is determined according to the area size of each fluorescent cluster in the fluorescent cluster segmentation image. The center of the fluorescent cluster is positioned according to the brightness distribution of the fluorescent cluster in the fluorescent cluster template and the maximum brightness point in the fluorescent cluster to obtain a cluster center. The application solves the technical problem that the conventional fluorescent cluster center positioning method is prone to failure in the case of fluorescent cluster adhesion, thereby failing to accurately position the center of the fluorescent cluster.

Description

Technical Field

[0001] This invention relates to the field of genome sequencing technology, and in particular to a method, apparatus, terminal device, and computer-readable storage medium for centrally locating fluorescent clusters. Background Technology

[0002] Whole-genome sequencing of biological samples, along with the mining and analysis of genomic variations, is of great significance for studying the origin, treatment, and prevention of diseases. High-throughput genome sequencing (NGS) technology, due to its advantages such as high parallelism, high throughput, high speed, low cost, and high accuracy, is widely used for the identification of genomic base sequences in microbial samples, model organisms, and human samples.

[0003] On the other hand, the localization of the fluorescent cluster center and the extraction of brightness are fundamental to the correct identification of bases. Traditional fluorescent cluster center localization mainly uses detection operators to detect and extract the outline of the fluorescent cluster, estimates the cluster center through circle fitting or centroid method, and then uses bilinear interpolation algorithm to calculate the brightness of the cluster center. The area within the outline of the fluorescent cluster is regarded as the foreground and the area outside the outline is regarded as the background. The brightness of the fluorescent cluster is obtained by subtracting the average brightness of its neighboring background area from the brightness of the cluster center.

[0004] However, in actual fluorescent cluster center localization and brightness extraction, there are often situations where fluorescent clusters are stuck together or even one fluorescent cluster wraps around another. In such cases, it is wrong to regard the area within the outline as a single fluorescent cluster. As a result, the traditional fluorescent cluster center localization method is very easy to fail, making it difficult to accurately locate the center of the fluorescent cluster.

[0005] The above content is only used to help understand the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention

[0006] The main objective of this invention is to provide a method, apparatus, terminal device, and computer-readable storage medium for center positioning of fluorescent clusters, aiming to solve the technical problem that traditional fluorescent cluster center positioning methods are prone to failure when fluorescent clusters are adhered, making it difficult to accurately center the fluorescent clusters.

[0007] This invention provides a method for centering a fluorescent cluster, which includes:

[0008] The brightness segmentation threshold of the sub-images of the fluorescence image is obtained by a preset clustering algorithm;

[0009] The sub-image is segmented according to the brightness segmentation threshold to obtain a fluorescence cluster segmentation image corresponding to the fluorescence image;

[0010] The fluorescent cluster template is determined based on the area size of each fluorescent cluster in the segmented image.

[0011] Based on the brightness distribution of the fluorescent clusters in the fluorescent cluster template and the maximum brightness point within the fluorescent cluster, the center of the fluorescent cluster is obtained by center positioning.

[0012] Optionally, the step of centering the fluorescent clusters based on the brightness distribution of the fluorescent clusters in the fluorescent cluster template and the maximum brightness point within the fluorescent clusters to obtain the cluster center includes:

[0013] The point with the maximum brightness within the fluorescent cluster in the fluorescent cluster template is selected as the undetermined center of the fluorescent cluster;

[0014] The coordinate offset of the center to be determined in each direction is calculated based on the brightness distribution of the fluorescent cluster;

[0015] The cluster center of the fluorescent cluster is obtained by performing a weighted calculation based on the coordinate offset to precisely locate the undetermined center.

[0016] Optionally, before the step of obtaining the brightness segmentation threshold of the sub-images of the fluorescence image using a preset clustering algorithm, the method further includes:

[0017] The fluorescence image is divided into multiple sub-images, and the brightness values ​​of the sub-images are obtained;

[0018] A brightness threshold is determined based on the brightness value of the sub-image, and the brightness values ​​of multiple sub-images are compared with the brightness threshold respectively;

[0019] If the brightness value of the sub-image is greater than the brightness threshold, then the high brightness data in the sub-image that is higher than the brightness threshold is removed, and the sub-image after removing the high brightness data is used as the standard brightness sub-image.

[0020] If the brightness value of the sub-image is less than or equal to the brightness threshold, then the sub-image is used as the standard brightness sub-image.

[0021] Optionally, the step of obtaining the brightness segmentation threshold of the sub-images of the fluorescence image using a preset clustering algorithm includes:

[0022] The standard brightness values ​​are binary-classified using a preset clustering algorithm to obtain a first cluster center and a second cluster center, wherein the standard brightness values ​​are the brightness values ​​of the standard brightness sub-images of the fluorescence image;

[0023] The average brightness value is determined based on the first cluster center and the second cluster center, and the average brightness value is used as the brightness segmentation threshold of the sub-images of the fluorescence image.

[0024] Optionally, the step of thresholding the sub-image according to the brightness segmentation threshold to obtain a fluorescence cluster segmentation image corresponding to the fluorescence image includes:

[0025] The sub-image is thresholded according to the brightness segmentation threshold to obtain a binary segmented image;

[0026] The binary segmented images are stitched together to obtain a fluorescence cluster segmentation image corresponding to the fluorescence image.

[0027] Optionally, the step of determining the fluorescent cluster template based on the area size of each fluorescent cluster in the segmented fluorescent cluster image includes:

[0028] The relationship between the area size of each fluorescent cluster in the segmented fluorescent cluster image and a preset fluorescent cluster area threshold is detected.

[0029] If the size relationship is such that the area of ​​the fluorescent cluster is greater than the fluorescent cluster area threshold, then the fluorescent cluster is determined to be an aggregated fluorescent cluster;

[0030] Obtain the position of the adhered fluorescent clusters in the fluorescent cluster segmentation image;

[0031] Obtain the target fluorescent cluster at the specified location in the comparison fluorescent cluster segmentation image, and use the target fluorescent cluster as the fluorescent cluster template of the adhered fluorescent cluster. The comparison fluorescent cluster segmentation image is a fluorescent cluster segmentation image with a different period than the fluorescent cluster segmentation image.

[0032] Optionally, after the step of centering the fluorescent cluster to obtain the cluster center, the method further includes:

[0033] The cluster center is determined as the center of a circle, and the average brightness of the pixels within a preset radius of the center of the circle is calculated;

[0034] The brightness of the fluorescent cluster is obtained by subtracting the background brightness value of the fluorescent image from the average brightness value of the pixels.

[0035] Furthermore, to achieve the above objectives, the present invention also provides a central positioning device for a fluorescent cluster, the central positioning device for the fluorescent cluster comprising:

[0036] The threshold acquisition module is used to obtain the brightness segmentation threshold of the sub-images of the fluorescence image through a preset clustering algorithm;

[0037] The segmentation module is used to perform threshold segmentation on the sub-image according to the brightness segmentation threshold to obtain a fluorescence cluster segmentation image corresponding to the fluorescence image;

[0038] The template determination module is used to determine the fluorescent cluster template based on the area size of each fluorescent cluster in the fluorescent cluster segmentation image;

[0039] The cluster center positioning module is used to locate the center of the fluorescent cluster based on the brightness distribution of the fluorescent clusters in the fluorescent cluster template and the maximum brightness point within the fluorescent cluster.

[0040] In this invention, the center positioning device for the fluorescent cluster implements the steps of the center positioning method for the fluorescent cluster described above when operating the aforementioned functional modules.

[0041] In addition, to achieve the above objectives, the present invention also provides a terminal device, the terminal device comprising: a memory, a processor, and a fluorescent cluster centering program stored in the memory and executable on the processor, wherein when the fluorescent cluster centering program is executed by the processor, it implements the steps of the fluorescent cluster centering method of the present invention as described above.

[0042] In addition, to achieve the above objectives, the present invention also provides a computer-readable storage medium storing a fluorescent cluster centering program, which, when executed by a processor, implements the steps of the fluorescent cluster centering method of the present invention as described above.

[0043] This invention provides a method, apparatus, terminal device, and computer-readable storage medium for center localization of fluorescent clusters. The method involves obtaining a brightness segmentation threshold for a sub-image of a fluorescent image using a preset clustering algorithm; performing threshold segmentation on the sub-image based on the brightness segmentation threshold to obtain a fluorescent cluster segmentation image corresponding to the fluorescent image; determining a fluorescent cluster template based on the area size of each fluorescent cluster in the fluorescent cluster segmentation image; and centering the fluorescent cluster to obtain the cluster center based on the brightness distribution of the fluorescent clusters in the fluorescent cluster template and the maximum brightness point within the fluorescent cluster.

[0044] This invention uses a preset clustering algorithm to obtain the brightness segmentation threshold of sub-images in a fluorescence image, and then performs threshold segmentation on the sub-images based on the brightness segmentation threshold to obtain a fluorescence cluster segmentation image corresponding to the fluorescence image. Then, a fluorescence cluster template is determined according to the area size of each fluorescence cluster contained in the fluorescence cluster segmentation image. Finally, the cluster center of the fluorescence cluster is accurately located by the brightness segmentation of the fluorescence cluster in the fluorescence cluster template and the maximum brightness point within the fluorescence cluster.

[0045] Thus, compared to traditional methods of locating the center of fluorescent clusters, this invention can effectively obtain templates for each fluorescent cluster by segmenting the fluorescence image. After selecting the point with the highest fluorescence cluster brightness value in the template for coarse localization, the cluster center is finally accurately located by combining the brightness distribution of the fluorescent cluster. In other words, this invention solves the technical problem that traditional methods of locating the center of fluorescent clusters are prone to failure when the clusters are adhered together, making accurate center localization difficult. Attached Figure Description

[0046] Figure 1 This is a schematic diagram of the hardware operating environment of the terminal device involved in the embodiments of the present invention;

[0047] Figure 2 This is a schematic flowchart illustrating the steps involved in an embodiment of the fluorescent cluster center localization method of the present invention;

[0048] Figure 3 This is a fluorescence image related to an embodiment of the method for centering fluorescent clusters according to the present invention;

[0049] Figure 4 This is a schematic flowchart illustrating the steps involved in another embodiment of the fluorescent cluster center localization method of the present invention;

[0050] Figure 5 This is a schematic diagram of the module of the fluorescent cluster center positioning device of the present invention.

[0051] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0052] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0053] The main solution of this invention is as follows: obtain the brightness segmentation threshold of the sub-images of the fluorescence image through a preset clustering algorithm; perform threshold segmentation on the sub-images according to the brightness segmentation threshold to obtain a fluorescence cluster segmentation image corresponding to the fluorescence image; determine the fluorescence cluster template according to the area size of each fluorescence cluster in the fluorescence cluster segmentation image; and locate the center of the fluorescence cluster by centering the fluorescence cluster according to the brightness distribution of the fluorescence clusters in the fluorescence cluster template and the maximum brightness point within the fluorescence cluster.

[0054] Whole-genome sequencing of biological samples, which allows for the mining and analysis of genomic variations, is of great significance for studying the origin, treatment, and prevention of diseases. Next-Generation Sequencing (NGS) technology, with its advantages of high parallelism, high throughput, high speed, low cost, and high accuracy, is widely used for the identification of genomic base sequences in microbial samples, model organisms, and human samples.

[0055] Fluorescent cluster center localization and brightness extraction are fundamental to accurate base identification. Traditional fluorescent cluster center localization mainly involves using detection operators to detect and extract the outline of the fluorescent cluster, estimating the cluster center through circle fitting or centroid method, and then using bilinear interpolation algorithm to calculate the brightness of the cluster center. The area within the outline of the fluorescent cluster is considered as the foreground, and the area outside the outline is considered as the background. The brightness of the fluorescent cluster is obtained by subtracting the average brightness of its neighboring background area from the brightness of the cluster center.

[0056] However, in actual fluorescent cluster center localization and brightness extraction, there are often situations where fluorescent clusters are stuck together or even one fluorescent cluster wraps around another. In such cases, it is wrong to regard the area within the outline as a single fluorescent cluster. As a result, the traditional fluorescent cluster center localization method is very easy to fail, making it difficult to accurately locate the center of the fluorescent cluster.

[0057] To address the aforementioned issues, this invention provides a solution. First, the fluorescence image is segmented into multiple non-overlapping sub-images. Then, the brightness values ​​of each sub-image are partitioned to remove high-brightness values. A preset clustering algorithm is used to perform binary classification on the remaining brightness values ​​of the sub-images, obtaining two cluster centers. The mean of the two cluster centers is set as the brightness segmentation threshold for threshold segmentation of the sub-images. This method is used to perform threshold segmentation on all sub-images, and the segmented sub-images are then stitched together, thereby achieving fluorescence image segmentation. Since a single period has four channels (A, G, C, T) of the fluorescence image, it is necessary to segment the fluorescence image across all four channels. For cases where fluorescence clusters are clustered, the four channels of a single period are insufficient to separate the clusters. However, the clustering of fluorescence clusters is extremely rare in a single period's fluorescence image. Therefore, by acquiring fluorescence images from multiple periods and segmenting them, templates for each fluorescence cluster can be obtained. The templates for each fluorescence cluster are used to detect the fluorescence cluster regions in each period's fluorescence image. Then, a weighted calculation of the fluorescence cluster brightness gradient is performed to accurately locate the cluster centers. Finally, taking the center of the fluorescent cluster as the center, calculate the average brightness of the pixels within a certain radius, and subtract the background brightness value from this brightness value to obtain the brightness of the fluorescent cluster.

[0058] Thus, compared to traditional methods of locating the center of fluorescent clusters, this invention can effectively obtain templates for each fluorescent cluster by segmenting the fluorescence image. After selecting the point with the highest fluorescence cluster brightness value in the template for coarse localization, the cluster center is then precisely located by combining the brightness distribution of the fluorescent cluster. Based on this, this invention can also use the precisely located fluorescent cluster center as the center of a circle, calculate the average brightness of pixels within a certain pixel radius, and subtract the background brightness value from this brightness value to obtain the brightness of the fluorescent cluster, thereby achieving the goal of accurately extracting the brightness of the fluorescent cluster.

[0059] like Figure 1 As shown, Figure 1 This is a schematic diagram of the terminal structure of the hardware operating environment involved in the embodiments of the present invention.

[0060] The terminal device in this embodiment of the invention can be any terminal device configured to control the positioning and brightness extraction of the fluorescent cluster center, such as a terminal server, a PC, or even a mobile terminal device such as a smartphone or tablet, or a non-mobile terminal device.

[0061] like Figure 1 As shown, the terminal device may include: a processor 1001, such as a CPU; a network interface 1004; a user interface 1003; a memory 1005; and a communication bus 1002. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen and an input unit such as a keyboard. Optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be high-speed RAM or non-volatile memory, such as a disk drive. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0062] Those skilled in the art will understand that Figure 1 The terminal structure shown does not constitute a limitation on the terminal device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0063] like Figure 1 As shown, the memory 1005, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and a central positioning program for the fluorescent cluster.

[0064] exist Figure 1In the terminal device shown, the network interface 1004 is mainly used to connect to the backend server and communicate with it; the user interface 1003 is mainly used to connect to the client (user terminal) and communicate with it; and the processor 1001 can be used to call the fluorescent cluster center positioning program stored in the memory 1005 and perform the following operations:

[0065] The brightness segmentation threshold of the sub-images of the fluorescence image is obtained by a preset clustering algorithm;

[0066] The sub-image is segmented according to the brightness segmentation threshold to obtain a fluorescence cluster segmentation image corresponding to the fluorescence image;

[0067] The fluorescent cluster template is determined based on the area size of each fluorescent cluster in the segmented image.

[0068] Based on the brightness distribution of the fluorescent clusters in the fluorescent cluster template and the maximum brightness point within the fluorescent cluster, the center of the fluorescent cluster is obtained by center positioning.

[0069] Furthermore, the processor 1001 can also be used to call the center localization program of the fluorescent cluster stored in the memory 1005 and perform the following operations:

[0070] The point with the maximum brightness within the fluorescent cluster in the fluorescent cluster template is selected as the undetermined center of the fluorescent cluster;

[0071] The coordinate offset of the center to be determined in each direction is calculated based on the brightness distribution of the fluorescent cluster;

[0072] The cluster center of the fluorescent cluster is obtained by performing a weighted calculation based on the coordinate offset to precisely locate the undetermined center.

[0073] Furthermore, the processor 1001 can also be used to call the fluorescence cluster center localization program stored in the memory 1005, and before executing the step of obtaining the brightness segmentation threshold of the sub-images of the fluorescence image through a preset clustering algorithm, it also performs the following operations:

[0074] The fluorescence image is divided into multiple sub-images, and the brightness values ​​of the sub-images are obtained;

[0075] A brightness threshold is determined based on the brightness value of the sub-image, and the brightness values ​​of multiple sub-images are compared with the brightness threshold respectively;

[0076] If the brightness value of the sub-image is greater than the brightness threshold, then the high brightness data in the sub-image that is higher than the brightness threshold is removed, and the sub-image after removing the high brightness data is used as the standard brightness sub-image.

[0077] If the brightness value of the sub-image is less than or equal to the brightness threshold, then the sub-image is used as the standard brightness sub-image.

[0078] Furthermore, the processor 1001 can also be used to call the center localization program of the fluorescent cluster stored in the memory 1005 and perform the following operations:

[0079] The standard brightness values ​​are binary-classified using a preset clustering algorithm to obtain a first cluster center and a second cluster center, wherein the standard brightness values ​​are the brightness values ​​of the standard brightness sub-images of the fluorescence image;

[0080] The average brightness value is determined based on the first cluster center and the second cluster center, and the average brightness value is used as the brightness segmentation threshold of the sub-images of the fluorescence image.

[0081] Furthermore, the processor 1001 can also be used to call the center localization program of the fluorescent cluster stored in the memory 1005 and perform the following operations:

[0082] The sub-image is thresholded according to the brightness segmentation threshold to obtain a binary segmented image;

[0083] The binary segmented images are stitched together to obtain a fluorescence cluster segmentation image corresponding to the fluorescence image.

[0084] Furthermore, the processor 1001 can also be used to call the center localization program of the fluorescent cluster stored in the memory 1005 and perform the following operations:

[0085] The relationship between the area size of each fluorescent cluster in the segmented fluorescent cluster image and a preset fluorescent cluster area threshold is detected.

[0086] If the size relationship is such that the area of ​​the fluorescent cluster is greater than the fluorescent cluster area threshold, then the fluorescent cluster is determined to be an aggregated fluorescent cluster;

[0087] Obtain the position of the adhered fluorescent clusters in the fluorescent cluster segmentation image;

[0088] Obtain the target fluorescent cluster at the specified location in the comparison fluorescent cluster segmentation image, and use the target fluorescent cluster as the fluorescent cluster template of the adhered fluorescent cluster. The comparison fluorescent cluster segmentation image is a fluorescent cluster segmentation image with a different period than the fluorescent cluster segmentation image.

[0089] Furthermore, the processor 1001 can also be used to call the center positioning program of the fluorescent cluster stored in the memory 1005, and after performing the step of center positioning of the fluorescent cluster to obtain the cluster center, perform the following operations:

[0090] The cluster center is determined as the center of a circle, and the average brightness of the pixels within a preset radius of the center of the circle is calculated;

[0091] The brightness of the fluorescent cluster is obtained by subtracting the background brightness value of the fluorescent image from the average brightness value of the pixels.

[0092] Based on the above hardware structure, various embodiments of the fluorescent cluster center localization method of the present invention are proposed.

[0093] Please refer to Figure 2 , Figure 2 This is a flowchart illustrating the steps involved in the first embodiment of the fluorescent cluster centering method of the present invention. It should be noted that although the logical order is shown in the flowchart, in some cases, the fluorescent cluster centering method of the present invention may, of course, execute the steps shown or described in a different order than that shown here.

[0094] In a first embodiment of the fluorescent cluster center localization method of the present invention, the executing entity of the fluorescent cluster center localization method of the present invention can be the aforementioned terminal device. Based on this, the fluorescent cluster center localization method of the present invention includes:

[0095] Step S10: Obtain the brightness segmentation threshold of the sub-images of the fluorescence image using a preset clustering algorithm;

[0096] In this embodiment, during the process of locating the center of the fluorescence cluster and extracting the brightness, the terminal device first obtains the brightness segmentation threshold of the sub-images of the fluorescence image through a preset clustering algorithm. There are multiple fluorescence images, which are fluorescence images obtained by the terminal device from image acquisition of the four channels A, G, C and T in multiple cycles.

[0097] It should be noted that, in this embodiment, the preset clustering algorithm is preferably the K-means clustering algorithm (an iterative clustering analysis algorithm), and the multiple periods are preferably five periods. Of course, different numbers of periods can be set based on the different design needs of actual applications.

[0098] Furthermore, due to the varying effects of biochemical reactions, the brightness of fluorescence clusters in different regions of the fluorescence image may differ significantly, and even within the same region, the brightness distribution of fluorescence clusters may be uneven. Therefore, traditional image segmentation algorithms, such as single-threshold methods, mean-shift algorithms, watershed algorithms, and level set segmentation algorithms, struggle to effectively segment densely populated areas of fluorescence clusters and regions with significant brightness differences. Consequently, the fluorescence cluster center localization method of this invention performs image segmentation on fluorescence images of different periods in each channel to detect fluorescence clusters.

[0099] Optionally, in a feasible embodiment, prior to step S10 above, the method for centering the fluorescent cluster of the present invention may further include:

[0100] Step A10: Divide the fluorescence image into multiple sub-images and obtain the brightness values ​​of the sub-images;

[0101] Step A20: Determine a brightness threshold based on the brightness value of each of the sub-images, and compare the brightness values ​​of the multiple sub-images with the brightness threshold respectively;

[0102] In this embodiment, before the terminal device begins to locate the center of the fluorescent clusters in the fluorescence image and extract the brightness, it first divides the fluorescence image into multiple sub-images and obtains the brightness value of each sub-image. Then, the brightness values ​​of each sub-image are arranged from smallest to largest. A brightness histogram is built based on the brightness value data of each sub-image. A brightness threshold is determined based on the principle of high brightness value and few pixels. Then, the brightness value of each sub-image is compared with the determined brightness threshold to remove high brightness data in the sub-image.

[0103] Step A30: If the brightness value of the sub-image is greater than the brightness threshold, then remove the high brightness data in the sub-image that is higher than the brightness threshold, and use the sub-image after removing the high brightness data as the standard brightness sub-image.

[0104] In this embodiment, the terminal device compares the brightness value of each sub-image with a determined brightness threshold. If the brightness value of the sub-image is greater than the brightness threshold, the high brightness data in the sub-image that is higher than the brightness threshold is removed, and the sub-image after removing the high brightness data is used as a standard brightness image to participate in subsequent calculations, so as to achieve more accurate detection of each fluorescent cluster.

[0105] Step A40: If the brightness value of the sub-image is less than the brightness threshold, then the sub-image is used as the standard brightness sub-image.

[0106] In this embodiment, if the brightness of a sub-image is less than the brightness threshold, the sub-image is directly used as the standard brightness sub-image in subsequent calculations.

[0107] Based on this, in a feasible embodiment, step S10 above, which obtains the brightness segmentation threshold of the sub-images of the fluorescence image through a preset clustering algorithm, may specifically include:

[0108] Step S101: The standard brightness value is binary classified by a preset clustering algorithm to obtain the first cluster center and the second cluster center, wherein the standard brightness value is the brightness value of the standard brightness sub-image of the fluorescence image;

[0109] Step S102: Determine the average brightness value based on the first cluster center and the second cluster center, and use the average brightness value as the brightness segmentation threshold of the sub-image of the fluorescence image.

[0110] In this embodiment, the terminal device uses the K-means clustering algorithm to perform binary classification on the standard brightness values ​​after removing high brightness values, and obtains the first cluster center and the second cluster center. The average value of the two cluster centers is taken as the brightness segmentation threshold of the sub-image of the fluorescence image, so as to segment the sub-image based on the brightness segmentation threshold.

[0111] Step S20: Perform threshold segmentation on the sub-image according to the brightness segmentation threshold to obtain a fluorescence cluster segmentation image corresponding to the fluorescence image;

[0112] In this embodiment, after determining the brightness segmentation threshold of the sub-image of the fluorescence image, the terminal device can perform threshold segmentation on the sub-convexities according to the brightness segmentation threshold to obtain a fluorescence cluster segmentation image corresponding to the fluorescence image.

[0113] Optionally, in a feasible embodiment, step S20 described above may include:

[0114] Step S201: Perform threshold segmentation on the sub-image according to the brightness segmentation threshold to obtain a binary segmented image;

[0115] Step S202: The binary segmented images are stitched together to obtain a fluorescence cluster segmented image corresponding to the fluorescence image.

[0116] In this embodiment, the terminal device takes the average value of the two cluster centers as the brightness segmentation threshold, performs threshold segmentation on the sub-images to obtain a binary segmented image, and finally stitches together the multiple segmented sub-images to obtain a complete fluorescence cluster segmentation image. By performing image segmentation on multiple periodic channel images using this method, the initial segmentation of fluorescence clusters can be achieved.

[0117] Step S30: Determine the fluorescent cluster template based on the area size of each fluorescent cluster in the fluorescent cluster segmentation image;

[0118] In this embodiment, after the terminal device segments the fluorescence image based on the K-means clustering algorithm to obtain a fluorescence cluster segmentation image, it obtains the area size of each fluorescence cluster in the fluorescence cluster segmentation image and determines the template of each fluorescence cluster based on the area size of each fluorescence cluster.

[0119] Optionally, in a feasible embodiment, step S30 described above may include:

[0120] S301, Detect the relationship between the area size of each fluorescent cluster in the fluorescent cluster segmentation image and the preset fluorescent cluster area threshold;

[0121] In this embodiment, the terminal device first estimates the area of ​​a single fluorescent cluster in the segmented fluorescence image, uses this area as a preset fluorescence cluster area threshold, and then detects the relationship between the size of each fluorescence cluster area in the segmented image and the fluorescence cluster area threshold.

[0122] Furthermore, in this embodiment, the preset fluorescence cluster area threshold can be set to different values ​​based on different design needs of actual applications.

[0123] S302, if the size relationship is such that the area of ​​the fluorescent cluster is greater than the fluorescent cluster area threshold, then the fluorescent cluster is determined to be an aggregated fluorescent cluster;

[0124] S303, Obtain the position of the adhered fluorescent cluster in the fluorescent cluster segmentation image;

[0125] In this embodiment, if the terminal device determines that the area of ​​the detected fluorescent cluster is greater than the fluorescent cluster area threshold, then the fluorescent cluster is determined to be an adherent fluorescent cluster. The terminal device obtains the location region of the adherent fluorescent cluster in the fluorescent cluster segmentation image, and the location region of the adherent fluorescent cluster is the adhesion region.

[0126] S304, obtain the target fluorescent cluster at the location in the comparison fluorescent cluster segmentation image, and use the target fluorescent cluster as the fluorescent cluster template of the adhered fluorescent cluster, wherein the comparison fluorescent cluster segmentation image is a fluorescent cluster segmentation image with a different period than the fluorescent cluster segmentation image.

[0127] In this embodiment, the terminal device acquires a target fluorescent cluster at the location of the adhered fluorescent cluster in a comparative fluorescent cluster segmentation image of different periods compared to the currently detected fluorescent cluster segmentation image. The target fluorescent cluster is the fluorescent cluster with the smallest area existing in the adhered region among multiple comparative fluorescent cluster segmentation images. This target fluorescent cluster is used as a fluorescent cluster template for detection of the adhered fluorescent clusters. That is, after the terminal device determines the adhered region, it compares the fluorescent cluster segmentation area of ​​that region in the fluorescent images of each channel of multiple periods after segmentation. By finding the fluorescent cluster region with the smallest area, this region can be regarded as the template for each fluorescent cluster, thereby obtaining the template for each adhered fluorescent cluster.

[0128] For example, in this embodiment, multiple fluorescent clusters are prone to sticking together in the fluorescence image (specifically, as shown in the example). Figure 3(The image region is defined within the bounded box). For mutually adhered fluorescent clusters, in the fluorescence images of a certain channel in different periods, the fluorescent clusters are very likely to exist individually. This phenomenon can be used to segment the adhered fluorescent clusters. Therefore, first, roughly estimate the area S of a single fluorescent cluster in the initially segmented fluorescence image. Regions with an area greater than 4S / 3 are considered to have fluorescent clusters adhering. After determining the adhered region, compare the segmented area of ​​the fluorescent clusters in that region in the fluorescence images of each channel in multiple periods. By finding the fluorescent cluster region with the smallest area, this region can be regarded as the template for each fluorescent cluster, thus obtaining the template for each adhered fluorescent cluster.

[0129] Step S40: Based on the brightness distribution of the fluorescent clusters in the fluorescent cluster template and the maximum brightness point within the fluorescent clusters, the center of the fluorescent clusters is located to obtain the cluster center.

[0130] In this embodiment, after determining that there is no adhesion in the fluorescent cluster template, the terminal device further determines the point with the maximum brightness in the fluorescent clusters present in the fluorescent cluster template as the preliminary cluster center of the fluorescent cluster. In this way, the center of the fluorescent cluster is coarsely located. Then, the terminal device further performs coordinate offset and weighted calculations in various directions based on the brightness distribution of the fluorescent cluster to further accurately locate the preliminary cluster center of the fluorescent cluster.

[0131] Optionally, in a feasible embodiment, step S40 described above may include:

[0132] Step S401: Select the point with the maximum brightness within the fluorescent cluster in the fluorescent cluster template as the undetermined center of the fluorescent cluster;

[0133] In this embodiment, the terminal device performs threshold segmentation on the sub-image using the K-means clustering algorithm, thereby obtaining a binary segmented image. Then, the terminal device calculates and labels the 8-connected regions of the binary segmented image, treating each 8-connected region as a fluorescent cluster within the sub-image block. Next, the terminal device searches for the pixel with the highest brightness—the maximum brightness point—within the corresponding region of each 8-connected region in the overall fluorescence image, and considers this as the preliminary cluster center of the fluorescent cluster.

[0134] Step S402: Calculate the coordinate offset of the center to be determined in each direction based on the brightness distribution of the fluorescent cluster;

[0135] Step S403: Perform a weighted calculation based on the coordinate offset to precisely locate the center to be determined and obtain the cluster center of the fluorescent cluster.

[0136] In this embodiment, since the brightness distribution within the fluorescent cluster region is not uniform, but the coordinates of the cluster center differ from the coordinates of the pixel with the highest brightness value within the region by no more than 1 pixel (i.e., the values ​​of adjacent pixels are relatively close), the terminal device, after taking the pixel with the highest brightness value within the fluorescent cluster region as the initial cluster center, assumes that the brightness of this center point is I. (u,v) Let (u,v) represent the coordinates of the point. Then, we take 8 points within the 8-connected region of this point: (u-1,v-1), (u-1,v), (u-1,v+1), (u,v-1), (u,v+1), (u+1,v-1), (u+1,v+1), and (u+1,v+1). The brightness of each point is I. (u-1,v-1) I (u-1,v) I (u-1,v+1) I (u,v-1) I (u,v+1) I (u+1,v-1) I (u+1,v) I (u+1,v+1) Thus, the terminal device uses a quadratic polynomial based on the brightness I. (u-1,v) I (u,v) I (u+1,v) The polynomial coefficients are calculated by fitting the coordinates of the polynomial, and the abscissa offset of the maximum point of the quadratic polynomial is denoted as α. Similarly, it can be calculated based on I. (u,v-1) I (u,v) I (u,v+1) The offset value of the vertical coordinate is β.

[0137] Furthermore, the terminal device utilizes a quadratic polynomial based on the brightness I (u-1,v-1) I (u,v) I (u+1,v+1) and its coordinates, and brightness I (u-1,v+1) I (u,v) I (u+1,v-1) The coordinates of the points where the maximum value of the quadratic polynomial is located can be fitted and calculated to determine the coordinate offsets ε and η of the points along the diagonal directions "\" and " / ". Specifically, the brightness gradient is calculated as follows:

[0138]

[0139] According to I 01 with I 02 The offset α of the horizontal axis is calculated as follows:

[0140]

[0141] According to I 10 with I 20 The offset β of the ordinate is calculated as follows:

[0142]

[0143] According to I 11 with I 22 The coordinate offset ε of the diagonal "\" is calculated as follows:

[0144]

[0145] According to I 21 with I 12 The coordinate offset η of the diagonal " / " is calculated as follows:

[0146]

[0147] Since the horizontal and vertical axes have different degrees of influence on the coordinates than the diagonal direction, the terminal device sets different weights to more accurately locate the center of the fluorescent cluster. In this way, the terminal device can obtain the center coordinates of the fluorescent cluster using the following calculation formula, thereby achieving precise positioning of the center of the fluorescent cluster.

[0148]

[0149] In this embodiment, during the process of locating the center of fluorescence clusters and extracting brightness, the terminal device first divides the fluorescence image into multiple non-overlapping sub-images. Then, the brightness values ​​of the sub-images are partitioned to remove high brightness values. A preset clustering algorithm is used to perform binary classification on the remaining brightness values ​​of the sub-images to obtain two cluster centers. The mean of the two cluster centers is set as the brightness segmentation threshold to perform threshold segmentation on the sub-images. This method is used to perform threshold segmentation on all sub-images, and the segmented sub-images are then stitched together, thereby achieving fluorescence image segmentation. For cases where fluorescence clusters are clustered together, a single-cycle fluorescence image is insufficient to separate the clusters. However, the clusters are very unlikely to cluster together in a single cycle of fluorescence images across multiple cycles. Therefore, by acquiring fluorescence images from multiple cycles and performing image segmentation, templates for each fluorescence cluster can be obtained. The fluorescent cluster regions in each periodic fluorescence image are detected using templates of each fluorescent cluster. Then, the point with the maximum brightness in the fluorescent clusters existing in the determined fluorescent cluster template is determined as the preliminary cluster center of the fluorescent cluster. This achieves coarse localization of the center of the fluorescent cluster. Afterward, the terminal device further calculates the coordinate offset and weighted values ​​in each direction based on the brightness distribution of the fluorescent cluster to further refine the localization of the preliminary cluster center.

[0150] Thus, compared to the traditional method of locating the center of fluorescent clusters, this invention divides the fluorescent image into multiple sub-images, uses the histogram method to partition the brightness values ​​of the sub-images to remove high brightness values, and uses the K-means clustering algorithm to flexibly obtain thresholds based on the changes in image brightness to perform threshold segmentation of the sub-images. By segmenting the multi-period fluorescent image, the templates of each fluorescent cluster can be obtained well, thereby achieving accurate detection of each fluorescent cluster region.

[0151] Furthermore, based on the first embodiment of the fluorescent cluster center localization method of the present invention described above, a second embodiment of the fluorescent cluster center localization method of the present invention is proposed. For example... Figure 4 As shown, Figure 4 This is a schematic flowchart illustrating the steps involved in the second embodiment of the fluorescent cluster center localization method of the present invention.

[0152] In this embodiment, after obtaining the cluster center by centering the fluorescent cluster in step S40 based on the brightness distribution of the fluorescent clusters in the fluorescent cluster template and the maximum brightness point within the fluorescent cluster, the method for centering the fluorescent cluster of the present invention may further include:

[0153] Step S50: Determine the cluster center as the center of a circle, and calculate the average brightness of pixels within a preset radius of the center of the circle;

[0154] Step S60: Subtract the background brightness value of the fluorescence image from the average brightness value of the pixels to obtain the brightness of the fluorescence cluster.

[0155] In this embodiment, after the terminal device achieves precise positioning of the center of the fluorescent cluster in the fluorescence image according to steps S10, S20, S30 and S40 of the fluorescent cluster center positioning method of the present invention, the terminal device can accurately locate the center of the fluorescent cluster as the center of a circle, calculate the average brightness of the pixels within a certain pixel range with a radius, and finally obtain the brightness of the fluorescent cluster by subtracting the background brightness value of the entire fluorescence image from the average brightness of the pixels.

[0156] For example, after determining the cluster center of the fluorescent cluster in the fluorescence image, the terminal device uses the coordinates of the cluster center as the center of a circle with a radius of 1 pixel, and calculates the average brightness of the pixels within the circle.

[0157] In the formula, I(u′,v′), I(u′-1,v′), I(u′+1,v′), I(u′,v′-1), I(u′,v′+1), It can be obtained through bilinear interpolation.

[0158] Then, the terminal device uses the binary segmented image obtained in step S201 to obtain a background region image, and uses the background region image to calculate the average brightness of the background region. Finally, the terminal device will calculate the average brightness of the pixels within the circular area. Subtract the average brightness value of the background area The brightness value of the fluorescent cluster can then be obtained.

[0159] In this embodiment, after the terminal device achieves precise positioning of the center of the fluorescent cluster in the fluorescence image, it can further calculate the average brightness of pixels within a certain pixel radius, using the precisely located cluster center as the center. Finally, by subtracting the background brightness value of the entire fluorescence image from the average pixel brightness, the brightness of the fluorescent cluster can be obtained. Thus, the fluorescent cluster center positioning method of this invention also achieves the goal of accurately extracting the brightness of the fluorescent cluster.

[0160] This application divides a fluorescence image into multiple sub-images and uses a histogram method to remove high-brightness values ​​from the sub-images. This allows the terminal device to flexibly obtain a brightness segmentation threshold based on image brightness changes using the K-means clustering algorithm for threshold segmentation of the sub-images. By segmenting the fluorescence image across multiple periods, templates for each fluorescence cluster can be effectively obtained, achieving accurate detection of each fluorescence cluster region. Furthermore, by initially selecting the point with the maximum brightness value of the fluorescence cluster as the cluster center, and calculating the brightness gradient distribution of the fluorescence cluster, the cluster center is precisely located through a weighted calculation of the brightness gradient. Finally, the brightness of the fluorescence cluster is obtained by subtracting the background brightness value from the average brightness of the pixels within the vicinity of the cluster center, thus achieving brightness extraction of the fluorescence cluster.

[0161] In addition, please refer to Figure 5 The present invention also proposes a central positioning device for fluorescent clusters, which includes:

[0162] The threshold acquisition module 10 is used to obtain the brightness segmentation threshold of the sub-images of the fluorescence image through a preset clustering algorithm;

[0163] The segmentation module 20 is used to perform threshold segmentation on the sub-image according to the brightness segmentation threshold to obtain a fluorescence cluster segmentation image corresponding to the fluorescence image;

[0164] Template determination module 30 is used to determine the fluorescent cluster template based on the area size of each fluorescent cluster in the fluorescent cluster segmentation image;

[0165] The cluster center positioning module 40 is used to locate the center of the fluorescent cluster based on the brightness distribution of the fluorescent clusters in the fluorescent cluster template and the maximum brightness point within the fluorescent cluster.

[0166] Preferably, the cluster center positioning module 40 includes:

[0167] The coarse positioning unit is used to select the point with the maximum brightness within the fluorescent cluster in the fluorescent cluster template as the undetermined center of the fluorescent cluster;

[0168] The fine positioning unit is used to calculate the coordinate offset of the center to be determined in each direction based on the brightness distribution of the fluorescent cluster; and to perform a weighted calculation according to the coordinate offset to finely locate the center to be determined and obtain the cluster center of the fluorescent cluster.

[0169] Preferably, the central positioning device for the fluorescent cluster of the present invention further includes:

[0170] A brightness threshold determination module is used to segment a fluorescence image into multiple sub-images and obtain the brightness value of the sub-images; and to determine a brightness threshold based on the brightness value of the sub-images, and to compare the brightness values ​​of the multiple sub-images with the brightness threshold respectively;

[0171] A standard brightness sub-unit determination module is used to remove high brightness data in the sub-image that is higher than the brightness threshold if the brightness value of the sub-image is greater than the brightness threshold, and to use the sub-image after removing the high brightness data as a standard brightness sub-image; and to use the sub-image as a standard brightness sub-image if the brightness value of the sub-image is less than or equal to the brightness threshold.

[0172] Preferably, the threshold acquisition module 10 includes:

[0173] A classification unit is used to perform binary classification on standard brightness values ​​using a preset clustering algorithm to obtain a first cluster center and a second cluster center, wherein the standard brightness value is the brightness value of the standard brightness sub-image of the fluorescence image;

[0174] A threshold determination unit is used to determine an average brightness value based on the first cluster center and the second cluster center, and to use the average brightness value as a brightness segmentation threshold for the sub-images of the fluorescence image.

[0175] Preferably, the segmentation module 20 includes:

[0176] A segmentation unit is used to perform threshold segmentation on the sub-image according to the brightness segmentation threshold to obtain a binary segmented image;

[0177] The stitching unit is used to stitch the binary segmented images to obtain a fluorescence cluster segmented image corresponding to the fluorescence image.

[0178] Preferably, the template determining module 30 includes:

[0179] The detection unit is used to detect the relationship between the area size of each fluorescent cluster in the fluorescent cluster segmentation image and a preset fluorescent cluster area threshold.

[0180] An adhering fluorescent cluster determination unit is used to determine that the fluorescent cluster is an adhering fluorescent cluster if the area of ​​the fluorescent cluster is greater than the area threshold of the fluorescent cluster.

[0181] A location acquisition unit is used to acquire the location of the adhering fluorescent clusters in the fluorescent cluster segmentation image;

[0182] The template determination unit is used to obtain the target fluorescent cluster at the location in the comparison fluorescent cluster segmentation image, and use the target fluorescent cluster as the fluorescent cluster template of the adhered fluorescent cluster, wherein the comparison fluorescent cluster segmentation image is a fluorescent cluster segmentation image with a different period than the fluorescent cluster segmentation image.

[0183] Preferably, the central positioning device for the fluorescent cluster of the present invention further includes:

[0184] A brightness extraction module is used to determine the cluster center as the center of a circle and calculate the average brightness of pixels within a preset radius of the center; and to subtract the background brightness value of the fluorescence image from the average brightness of the pixels to obtain the brightness of the fluorescence cluster.

[0185] The functional modules of the fluorescent cluster center positioning device proposed in this embodiment implement the steps of the fluorescent cluster center positioning method as described above during operation, which will not be repeated here.

[0186] Furthermore, embodiments of the present invention also propose a computer-readable storage medium storing a centering program for a fluorescent cluster, wherein the centering program for the fluorescent cluster, when executed by a processor, implements the steps of the centering method for the fluorescent cluster as described above.

[0187] Specific embodiments of the computer-readable storage medium of the present invention can be found in the above-described embodiments of the fluorescent cluster center localization method, and will not be repeated here.

[0188] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0189] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0190] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0191] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A method for centering a fluorescent cluster, comprising: The center positioning method of the fluorescent cluster comprises: cutting the fluorescent image into a plurality of sub-images and obtaining the brightness values of the sub-images; determining a brightness threshold value based on the brightness values of the sub-images and comparing the brightness values of the plurality of sub-images with the brightness threshold value respectively; if the brightness value of the sub-image is greater than the brightness threshold value, removing the high brightness data higher than the brightness threshold value in the sub-image, and taking the sub-image after removing the high brightness data as a standard brightness sub-image; if the brightness value of the sub-image is less than or equal to the brightness threshold value, taking the sub-image as a standard brightness sub-image; obtaining a brightness segmentation threshold value of the sub-image of the fluorescent image through a preset clustering algorithm; performing threshold segmentation on the sub-image according to the brightness segmentation threshold value to obtain a fluorescent cluster segmentation image corresponding to the fluorescent image; determining a fluorescent cluster template according to the area size of each fluorescent cluster in the fluorescent cluster segmentation image, wherein the step of determining the fluorescent cluster template according to the area size of each fluorescent cluster in the fluorescent cluster segmentation image comprises: detecting the size relationship between the area size of each fluorescent cluster in the fluorescent cluster segmentation image and a preset fluorescent cluster area threshold value; if the size relationship is that the area of the fluorescent cluster is greater than the fluorescent cluster area threshold value, determining that the fluorescent cluster is a conglutinant fluorescent cluster; obtaining the position of the conglutinant fluorescent cluster in the fluorescent cluster segmentation image; obtaining a target fluorescent cluster at the position in a contrast fluorescent cluster segmentation image, and taking the target fluorescent cluster as the fluorescent cluster template of the conglutinant fluorescent cluster, wherein the contrast fluorescent cluster segmentation image is a fluorescent cluster segmentation image of a different period from the fluorescent cluster segmentation image; performing center positioning on the fluorescent cluster according to the brightness distribution of the fluorescent cluster in the fluorescent cluster template and the brightness maximum point in the fluorescent cluster to obtain a cluster center.

2. The method of centering a fluorescent cluster of claim 1, wherein, The step of performing center positioning on the fluorescent cluster according to the brightness distribution of the fluorescent cluster in the fluorescent cluster template and the brightness maximum point in the fluorescent cluster to obtain a cluster center comprises: selecting the brightness maximum point in the fluorescent cluster in the fluorescent cluster template as a to-be-determined center of the fluorescent cluster; calculating the coordinate offset of each direction of the to-be-determined center according to the brightness distribution of the fluorescent cluster; performing weighted calculation according to the coordinate offset to finely position the to-be-determined center to obtain the cluster center of the fluorescent cluster.

3. The method of centering a fluorescent cluster of claim 1, wherein, The step of obtaining the brightness segmentation threshold value of the sub-image of the fluorescent image through a preset clustering algorithm comprises: performing two classification on a standard brightness value through a preset clustering algorithm to obtain a first clustering center and a second clustering center, wherein the standard brightness value is the brightness value of the standard brightness sub-image of the fluorescent image; determining a brightness average value based on the first clustering center and the second clustering center, and taking the brightness average value as the brightness segmentation threshold value of the sub-image of the fluorescent image.

4. The method of centering a fluorescent cluster of claim 1, wherein, The step of performing threshold segmentation on the sub-image according to the brightness segmentation threshold value to obtain a fluorescent cluster segmentation image corresponding to the fluorescent image comprises: performing threshold segmentation on the sub-image according to the brightness segmentation threshold value to obtain a binary segmentation image; The binary segmented image is spliced to obtain a fluorescent cluster segmented image corresponding to the fluorescent image.

5. The method of centering a fluorescent cluster according to any one of claims 1 to 4, wherein, After the step of center positioning of the fluorescent cluster to obtain a cluster center, the method further comprises: determining the cluster center as a circle center and calculating an average value of pixel point brightness within a preset radius range of the circle center; subtracting the background brightness value of the fluorescent image from the average value of pixel point brightness to obtain the brightness of the fluorescent cluster.

6. A device for centering a fluorescent cluster, characterized in that The center positioning device of the fluorescent cluster comprises: a threshold acquisition module configured to acquire a brightness segmentation threshold of a sub-image of the fluorescent image by using a preset clustering algorithm; a segmentation module configured to perform threshold segmentation on the sub-image according to the brightness segmentation threshold to obtain a fluorescent cluster segmented image corresponding to the fluorescent image; a template determination module configured to determine a fluorescent cluster template according to the area size of each fluorescent cluster in the fluorescent cluster segmented image, wherein the template determination module is specifically configured to detect the size relationship between the area size of each fluorescent cluster in the fluorescent cluster segmented image and a preset fluorescent cluster area threshold; if the size relationship is that the area of the fluorescent cluster is greater than the fluorescent cluster area threshold, the fluorescent cluster is determined as a conglutinated fluorescent cluster; the position of the conglutinated fluorescent cluster in the fluorescent cluster segmented image is acquired; a target fluorescent cluster at the position in a contrast fluorescent cluster segmented image is acquired, and the target fluorescent cluster is taken as the fluorescent cluster template of the conglutinated fluorescent cluster, wherein the contrast fluorescent cluster segmented image is a fluorescent cluster segmented image of a different period from the fluorescent cluster segmented image; a cluster center positioning module configured to perform center positioning on the fluorescent cluster according to the brightness distribution of the fluorescent cluster in the fluorescent cluster template and the maximum brightness point in the fluorescent cluster to obtain a cluster center. The center positioning device of the fluorescent cluster further comprises: dividing the fluorescent image into a plurality of sub-images and acquiring the brightness values of the sub-images; determining a brightness threshold based on the brightness values of the sub-images and comparing the brightness values of the plurality of sub-images with the brightness threshold respectively; if the brightness value of the sub-image is greater than the brightness threshold, the high-brightness data higher than the brightness threshold in the sub-image is removed, and the sub-image after removing the high-brightness data is taken as a standard brightness sub-image; if the brightness value of the sub-image is less than or equal to the brightness threshold, the sub-image is taken as a standard brightness sub-image.

7. A terminal device, characterized by comprising: The terminal device comprises a memory, a processor, and a fluorescent cluster center positioning program stored on the memory and executable on the processor, and the fluorescent cluster center positioning program, when executed by the processor, implements the steps of the fluorescent cluster center positioning method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a fluorescent cluster center positioning program, and the fluorescent cluster center positioning program, when executed by the processor, implements the steps of the fluorescent cluster center positioning method according to any one of claims 1 to 5.

Images