Method and device for determining reference fluorescence image, computer equipment, readable storage medium and program product

Abstract

The invention relates to a reference fluorescence image determination method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring at least two candidate fluorescence images; the candidate fluorescence image comprises at least two areas; for each region in each candidate fluorescence image, determining region correlation between the region and corresponding regions in other candidate fluorescence images, and determining target region correlation corresponding to the region based on each region correlation; determining target image correlation corresponding to the candidate fluorescence image according to the target region correlation corresponding to each region in the candidate fluorescence image; and based on the target image correlation corresponding to each candidate fluorescence image, determining a reference fluorescence image from each candidate fluorescence image. By adopting the method, the reference fluorescence image can be determined more accurately.

Description

Technical Field

[0001] The present application relates to the field of gene sequencing technology, and in particular to a method, apparatus, computer device, computer-readable storage medium and computer program product for determining a reference fluorescence image. Background Art

[0002] Gene sequencers are devices used for gene sequencing, detection and generation of raw data of species gene sequences. Gene sequencers are high-tech equipment that combines multidisciplinary technologies, including instrument direction, reagent direction, etc., and have extremely high requirements for each technical direction. The instrument direction includes electronic information, intelligent algorithms, mechanical control, optics, fluids, chip design, bioinformatics, etc.; the reagent direction includes protein, raw materials, biochemistry, etc.

[0003] Most of the gene sequencers on the target market rely on the collection, recognition and registration of fluorescent images, and finally extract the original data of the gene sequence from the fluorescent image (commonly known as: upstream), which is provided to the downstream for bioinformatics analysis (bioinformatics analysis), thereby generating a gene sequencing report. It can be seen that the accuracy of the data depends greatly on the fluorescent image to ensure the generation of high-quality data. Among them, the sequencing chip is called a flow cell, and there are multiple flow channels (Lane channels) on the flow cell, where chemical reagents flow to produce chemical reactions. When the gene fragment reacts, fluorescence is generated under the excitation of the laser, and then these fluorescent points are photographed by a camera to obtain fluorescent images, and then these fluorescent images can be registered.

[0004] However, the conventional method for determining the reference fluorescence image usually uses the first acquired fluorescence image as the reference fluorescence image for registration, which results in inaccurate determination of the reference fluorescence image. Summary of the invention

[0005] Based on this, it is necessary to provide a method, apparatus, computer device, computer-readable storage medium and computer program product for determining a reference fluorescence image that can improve accuracy in order to solve the above technical problems.

[0006] In a first aspect, the present application provides a method for determining a reference fluorescent image, comprising:

[0007] Acquire at least two candidate fluorescent images; the candidate fluorescent images include at least two regions;

[0008] For each region in each candidate fluorescent image, determining a region correlation between the region and corresponding regions in other candidate fluorescent images, and determining a target region correlation corresponding to the region based on each of the region correlations;

[0009] Determining a target image correlation corresponding to the candidate fluorescent image according to a target region correlation corresponding to each region in the candidate fluorescent image;

[0010] Based on the target image correlation corresponding to each candidate fluorescent image, a reference fluorescent image is determined from each candidate fluorescent image.

[0011] In one embodiment, determining the target region correlation corresponding to the region based on the correlations of the respective regions includes:

[0012] The region correlations corresponding to the regions are added together to obtain the target region correlation corresponding to the regions.

[0013] In one embodiment, determining the target image correlation corresponding to the candidate fluorescent image according to the target region correlation corresponding to each region in the candidate fluorescent image includes:

[0014] The target region correlation corresponding to each region in the candidate fluorescent image is added together to obtain the target image correlation corresponding to the candidate fluorescent image.

[0015] In one embodiment, acquiring at least two candidate fluorescence images comprises:

[0016] When the gene fragments react to generate fluorescence, a fluorescence image sequence is obtained by photographing with a camera module of a sequencing instrument; the fluorescence image sequence includes at least two initial fluorescence images;

[0017] The initial fluorescence image is downsampled to obtain at least two candidate fluorescence images.

[0018] In one embodiment, determining, for each region in each candidate fluorescent image, the region correlation between the region and corresponding regions in other candidate fluorescent images includes:

[0019] For each region in each candidate fluorescent image, extract pixel values ​​from the region and arrange the pixel values ​​into a one-dimensional vector;

[0020] A cosine correlation algorithm is used to determine the regional correlation between the one-dimensional vector of the region and the one-dimensional vectors of corresponding regions in other candidate fluorescent images.

[0021] In one embodiment, the method further comprises:

[0022] The reference fluorescence image is used as a reference to register the fluorescence image to be registered with the reference fluorescence image.

[0023] In a second aspect, the present application further provides a device for determining a reference fluorescent image, comprising:

[0024] A fluorescence image acquisition module, used to acquire at least two candidate fluorescence images; the candidate fluorescence images include at least two areas;

[0025] A region correlation determination module, used to determine, for each region in each candidate fluorescent image, a region correlation between the region and corresponding regions in other candidate fluorescent images, and determine a target region correlation corresponding to the region based on each of the region correlations;

[0026] An image correlation determination module, used to determine the target image correlation corresponding to the candidate fluorescent image according to the target region correlation corresponding to each region in the candidate fluorescent image;

[0027] The reference fluorescent image determination module is used to determine the reference fluorescent image from each candidate fluorescent image based on the target image correlation corresponding to each candidate fluorescent image.

[0028] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0029] Acquire at least two candidate fluorescent images; the candidate fluorescent images include at least two regions;

[0030] For each region in each candidate fluorescent image, determining a region correlation between the region and corresponding regions in other candidate fluorescent images, and determining a target region correlation corresponding to the region based on each of the region correlations;

[0031] Determining a target image correlation corresponding to the candidate fluorescent image according to a target region correlation corresponding to each region in the candidate fluorescent image;

[0032] Based on the target image correlation corresponding to each candidate fluorescent image, a reference fluorescent image is determined from each candidate fluorescent image.

[0033] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0034] Acquire at least two candidate fluorescent images; the candidate fluorescent images include at least two regions;

[0035] For each region in each candidate fluorescent image, determining a region correlation between the region and corresponding regions in other candidate fluorescent images, and determining a target region correlation corresponding to the region based on each of the region correlations;

[0036] Determining a target image correlation corresponding to the candidate fluorescent image according to a target region correlation corresponding to each region in the candidate fluorescent image;

[0037] Based on the target image correlation corresponding to each candidate fluorescent image, a reference fluorescent image is determined from each candidate fluorescent image.

[0038] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0039] Acquire at least two candidate fluorescent images; the candidate fluorescent images include at least two regions;

[0040] For each region in each candidate fluorescent image, determining a region correlation between the region and corresponding regions in other candidate fluorescent images, and determining a target region correlation corresponding to the region based on each of the region correlations;

[0041] Determining a target image correlation corresponding to the candidate fluorescent image according to a target region correlation corresponding to each region in the candidate fluorescent image;

[0042] Based on the target image correlation corresponding to each candidate fluorescent image, a reference fluorescent image is determined from each candidate fluorescent image.

[0043] The above-mentioned method, apparatus, computer device, computer-readable storage medium and computer program product for determining a reference fluorescence image obtain at least two candidate fluorescence images, wherein the candidate fluorescence images include at least two regions; for each region in each candidate fluorescence image, the region correlation between the region and the corresponding region in other candidate fluorescence images is determined, and based on the correlations of each region, the target region correlation corresponding to the region is accurately determined, and then based on the target region correlation corresponding to each region in the candidate fluorescence image, the target image correlation corresponding to the candidate fluorescence image is accurately determined. Then, based on the target image correlation corresponding to each candidate fluorescence image, the reference fluorescence image can be accurately determined from each candidate fluorescence image. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0045] Figure 1 A diagram of an application environment of a method for determining a reference fluorescent image in an embodiment;

[0046] Figure 2 is a schematic diagram of a fluorescent image in one embodiment;

[0047] Figure 3 is a schematic diagram of a registration area of ​​a fluorescence image to be registered in one embodiment;

[0048] Figure 4 is a schematic diagram of bubbles existing in a field of view according to an embodiment;

[0049] Figure 5 is a schematic diagram of a spot image of an embodiment;

[0050] Figure 6 is a schematic diagram of an initial correlation distribution diagram in one embodiment;

[0051] Figure 7 A schematic diagram of determining the side length of a correlation region in one embodiment;

[0052] Figure 8 is a structural block diagram of a device for determining a reference fluorescent image in one embodiment;

[0053] Fig. 9 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0055] In one embodiment, Figure 1 As shown, a method for determining a reference fluorescent image is provided. This embodiment uses the method applied to a computer device as an example for illustration. The computer device may be a terminal or a server. It is understandable that the method may also be applied to a system including a terminal and a server, and implemented through the interaction between the terminal and the server. Among them, the terminal may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things devices may be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, projection devices, etc. Portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. The head-mounted devices may be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc. The server may be an independent physical server, or a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides cloud computing services.

[0056] In this embodiment, determining the reference fluorescent image includes the following steps:

[0057] Step S102, acquiring at least two candidate fluorescence images; the candidate fluorescence images include at least two regions.

[0058] When the gene fragment reacts, fluorescence is generated under the excitation of the laser; the fluorescence image sequence is acquired through the camera module of the sequencing instrument; the reference fluorescence image and the fluorescence image to be registered are determined from the fluorescence image sequence. The camera module acquires the fluorescence image sequence through the light propagation path (optical path) of the lens, filter, and camera. The camera module can be a single optical path system or a multi-optical path system, and the multi-optical path system can be a dual optical path system or a quad optical path system.

[0059] Some single optical path systems are a combination of a lens (microscope), a filter, and a camera. Some dual optical path systems are a combination of a lens, two filters, and a camera; some quad optical path systems are a combination of two lenses, two filters per lens, and two cameras. The number of optical paths depends on how many different paths a point on the object can take to become a point on the image.

[0060] For example, the flow cell of a gene sequencing chip has 4 channels, each of which is virtually divided into 5 rows (Swath) x 80 columns (Tile) of small grids, a total of 1600 grids, also known as FOV (field of view), with hundreds of thousands of such clusters (fluorescent spots, clusters) in each field of view. Figure 2 shown.

[0061] It is understandable that the cluster points have fixed spatial coordinates on the chip, but due to mechanical errors, the positions of the cluster points in the fluorescence images obtained in each field of view have certain deviations. Therefore, it is necessary to use the camera module of the sequencing instrument to capture the field of view in each round of reaction to obtain a fluorescence image sequence and align the fluorescence images so that the cluster points can fall into the theoretically corresponding positions.

[0062] Optionally, the computer device obtains a fluorescence image sequence by photographing with a camera module, where the fluorescence image sequence includes at least two candidate fluorescence images, and each candidate fluorescence image is divided into at least two areas.

[0063] The fluorescence image sequence may include K images, where K is greater than or equal to 2, such as K= 12~20.

[0064] Exemplarily, the computer device divides each candidate fluorescent image into N x N equally divided regions (Roi), for example: N=3, that is, the candidate fluorescent image is divided into 3 x 3 equally divided regions, where Represents the region at row 1 and column 2 in the candidate fluorescence image.

[0065] Optionally, obtaining at least two candidate fluorescence images includes: when the gene fragment reaction produces fluorescence, obtaining a fluorescence image sequence by photographing with a camera module of a sequencing instrument; the fluorescence image sequence includes at least two initial fluorescence images; and downsampling the initial fluorescence image to obtain at least two candidate fluorescence images.

[0066] The computer device downsamples the initial fluorescent image by pixel merging or other methods, such as deleting pixels, which are not limited here.

[0067] For example, the computer device uses pixel merging to downsample the initial fluorescence image, synthesizing every 8x8 pixels in the initial fluorescence image into a new pixel, namely bin8. A 3000x3000 initial fluorescence image is downsampled to obtain a 375x375 candidate fluorescence image.

[0068] The computer device first downsamples the initial fluorescence image and then performs correlation operation, which can reduce the amount of calculation without changing the effect.

[0069] Step S104 , for each region in each candidate fluorescent image, determining the region correlation between the region and corresponding regions in other candidate fluorescent images, and determining the target region correlation corresponding to the region based on the correlations of the respective regions.

[0070] The other candidate fluorescence images are the candidate fluorescence images other than the targeted candidate fluorescence image in at least two candidate fluorescence images, and the regions between every two candidate fluorescence images correspond to each other. The target region correlation is the correlation finally determined between the region in the targeted candidate fluorescence image and the corresponding region in the other candidate fluorescence images.

[0071] Optionally, for each region in each candidate fluorescence image, the computer uses a regional correlation evaluation algorithm to determine the regional correlation between the region and corresponding regions in other candidate fluorescence images. The regional correlation evaluation algorithm can be set as needed, such as a cosine correlation algorithm, a spectral phase correlation method, or a template difference correlation method.

[0072] Optionally, for each region in each candidate fluorescence image, the regional correlation between the region and the corresponding regions in other candidate fluorescence images is determined, including: for each region in each candidate fluorescence image, pixel values ​​are extracted from the region and each pixel value is arranged into a one-dimensional vector; and a cosine correlation algorithm is used to determine the regional correlation between the one-dimensional vector of the region and the one-dimensional vector of the corresponding region in other candidate fluorescence images.

[0073] Optionally, the computer device determines the regional correlation between the one-dimensional vector of the region and the one-dimensional vectors of corresponding regions in other candidate fluorescent images using the following formula:

[0074]

[0075] in, and are the one-dimensional vector of the region and the one-dimensional vector of the corresponding region in other candidate fluorescence images, and are the values ​​of these two one-dimensional vectors in the i-th dimension, and They are and The model, express and The dot product of is the angle between two one-dimensional vectors, It is the regional correlation (Relation value) between the one-dimensional vector of the region and the one-dimensional vector of the corresponding region in other candidate fluorescence images.

[0076] Optionally, determining the target region correlation corresponding to the region based on the correlations of the respective regions includes: adding the correlations of the respective regions corresponding to the region to obtain the target region correlation corresponding to the region.

[0077] For example, for the candidate fluorescence image region, determine the The corresponding region and other candidate fluorescence images The regional correlation between regions is calculated by adding the correlations of each region to obtain the candidate fluorescence image. The target region relevance corresponding to the region.

[0078] Optionally, the computer device may also perform weighted summation of the regional correlations corresponding to the region to obtain the target regional correlation corresponding to the region.

[0079] The weight factor of each region correlation is negatively correlated with the distance between the other candidate fluorescent images to which the region belongs and the targeted candidate fluorescent image. That is, the closer the distance between the other candidate fluorescent images to which the region belongs and the targeted candidate fluorescent image, the greater the correlation between the other candidate fluorescent images and the targeted candidate fluorescent image, and the greater the weight factor of the region correlation corresponding to the region in the other candidate fluorescent images.

[0080] Optionally, the computer device may also average the regional correlations corresponding to the region to obtain the target region correlation corresponding to the region.

[0081] Optionally, the computer device may also determine the target region correlation corresponding to the region in other ways, which are not limited here.

[0082] Step S106 , determining the target image correlation corresponding to the candidate fluorescent image according to the target region correlation corresponding to each region in the candidate fluorescent image.

[0083] The target image correlation is the correlation finally determined between the target candidate fluorescent image and other candidate fluorescent images.

[0084] Optionally, determining the target image correlation corresponding to the candidate fluorescent image based on the target region correlation corresponding to each region in the candidate fluorescent image includes: adding the target region correlation corresponding to each region in the candidate fluorescent image to obtain the target image correlation corresponding to the candidate fluorescent image.

[0085] Exemplarily, the candidate fluorescent image includes N×N regions, the target region correlation corresponding to each region is obtained, and the target region correlations corresponding to each region are added together to obtain the target image correlation (Relation_k) corresponding to the candidate fluorescent image.

[0086] Optionally, the computer device may also perform weighted summation of the target region correlation corresponding to each region in the candidate fluorescent image to obtain the target image correlation corresponding to the candidate fluorescent image.

[0087] Among them, the weight factor of each target region correlation is negatively correlated with the distance between the position of the region in the candidate fluorescent image and the central region. That is, the closer the distance between the position of the region in the candidate fluorescent image and the central region is, the closer the region is to the central region of the image, and the larger the weight factor of the target region correlation corresponding to the region is.

[0088] Optionally, the computer device may also average the target region correlations corresponding to various regions in the candidate fluorescent image to obtain the target image correlation corresponding to the candidate fluorescent image.

[0089] Optionally, the computer device may also determine the correlation between the candidate fluorescent image and the target image by other methods, which are not limited here.

[0090] Step S108 : determining a reference fluorescent image from each candidate fluorescent image based on the target image correlation corresponding to each candidate fluorescent image.

[0091] The reference fluorescence image is an image used as a reference in the fluorescence image registration process.

[0092] Optionally, the computer device determines the reference fluorescence image from among the candidate fluorescence images the one with the greatest correlation with the target image.

[0093] Optionally, the computer device determines the reference fluorescence image from among the candidate fluorescence images the image with the second largest correlation with the target image.

[0094] It is understandable that during the sequencing process of sequencing images, the center offset of the image is extremely small (generally not more than 20 pixels). In this case, a small area is selected for cosine correlation calculation. The correlation between normal images is high, and the correlation between interference images and normal images is low. When a large number of images are compared and accumulated for correlation, statistical characteristics are presented. The image with the highest correlation is most likely to be the highest quality image. Therefore, the computer device can accurately determine the benchmark fluorescent image from each candidate fluorescent image based on the correlation of the target image corresponding to each candidate fluorescent image.

[0095] The above-mentioned method for determining the reference fluorescence image obtains at least two candidate fluorescence images, and the candidate fluorescence images include at least two regions; for each region in each candidate fluorescence image, the regional correlation between the region and the corresponding region in other candidate fluorescence images is determined, and the target region correlation corresponding to the region is accurately determined based on the correlation of each region, and then the target image correlation corresponding to the candidate fluorescence image is accurately determined based on the target region correlation corresponding to each region in the candidate fluorescence image. Then, based on the target image correlation corresponding to each candidate fluorescence image, the reference fluorescence image can be accurately determined from each candidate fluorescence image.

[0096] In one embodiment, the method further comprises: registering the fluorescence image to be registered with the reference fluorescence image based on the reference fluorescence image.

[0097] Optionally, the computer device registers the fluorescence image to be registered with the reference fluorescence image to obtain a registration result between the reference fluorescence image and the fluorescence image to be registered; the fluorescence image to be registered includes at least two registration areas, and the at least two registration areas include a central registration area.

[0098] The fluorescence image to be registered and the reference fluorescence image satisfy that the deflection angle, scaling and deformation (image distortion) are all less than a preset threshold. The fluorescence image to be registered and the reference fluorescence image can be a fluorescence image collected by a single optical path system or a fluorescence image collected by a multi-optical path system.

[0099] Optionally, the computer device may determine the first fluorescence image from the fluorescence image sequence as the reference fluorescence image, or may determine any fluorescence image from the fluorescence image sequence as the reference fluorescence image, which is not limited here.

[0100] Optionally, the fluorescence image to be registered includes at least two registration areas, the at least two registration areas include a central registration area, and also include at least one non-central registration area; correspondingly, the reference fluorescence image includes at least two reference areas, the at least two reference areas include a central reference area, and also include at least one non-central reference area. Wherein, the registration areas and the reference areas correspond one to one, the central registration area is an area at the central position of the fluorescence image to be registered, the non-central registration area is an area at the non-central position of the fluorescence image to be registered, the central reference area is an area at the central position of the reference fluorescence image, and the non-central reference area is an area at the non-central position of the reference fluorescence image.

[0101] Optionally, the at least two registration areas include a central registration area and four non-central registration areas, and the four non-central registration areas are located at different non-central positions.

[0102] like Figure 3 As shown, the registration areas are set at the center and four corners of the fluorescence image to be registered, and the side length of each registration area is 0.065~0.1 of the side length of the fluorescence image to be registered. For example, when the size of the fluorescence image to be registered is 3000x3000, the area size of the registration area is 200x200 or 300x300. Statistics show that when interference factors such as bubbles, impurities, and light spots appear in the flow cell, the probability that all five registration areas are covered by interference factors is extremely low, which can prove the effectiveness of the registration area division method, and it will not affect the use of more computing resources. The size of the reference area and the corresponding registration area are the same. As shown Figure 4 The image shown here shows bubbles in the field of view. Figure 5 Shown is a spot image.

[0103] Optionally, the fluorescence image to be registered is registered with the reference fluorescence image to obtain a registration result between the reference fluorescence image and the fluorescence image to be registered, including: step S202, determining the central area correlation between the central registration area and the central reference area corresponding to the reference fluorescence image; step S204, if the central area correlation is less than or equal to a first correlation threshold, obtaining the deviation value between each registration area and the corresponding reference area in the reference fluorescence image; step S206, determining the registration result between the reference fluorescence image and the fluorescence image to be registered based on the deviation values ​​corresponding to each registration area.

[0104] Step S202 : determining a central region correlation between a central registration region and a central reference region corresponding to the reference fluorescence image.

[0105] The computer device uses a correlation evaluation algorithm to determine the central region correlation between the central registration region and the central reference region corresponding to the reference fluorescence image, wherein the correlation evaluation algorithm can be set as needed.

[0106] Optionally, the computer device determines a target pixel point having the strongest correlation between the central registration area and a central reference area corresponding to the reference fluorescent image, and uses the correlation of the target pixel point as the central area correlation.

[0107] Optionally, the computer device determines a target pixel point at a second strongest correlation or a center position between the central registration area and a central reference area corresponding to the reference fluorescent image, and uses the correlation of the target pixel point as the central area correlation.

[0108] Step S204: if the central region correlation is less than or equal to the first correlation threshold, then obtaining a deviation value between each registration region and a corresponding reference region in the reference fluorescence image.

[0109] The first correlation threshold can be set as needed and is not limited here. The offset value is the value of the coordinate deviation between the registration area and the reference area. For example, the offset value (Offset) can be the sub-pixel deviation value between the registration area and the reference area in the x direction and the y direction.

[0110] Optionally, for each registration area and the corresponding reference area in the reference fluorescence image, the computer device traverses each pixel in the registration area and each pixel in the reference area, determines the pixel pair with the strongest correlation between the registration area and the reference area, and uses the deviation value between the pixel point of the registration area and the center pixel point in the pixel pair as the deviation value between the registration area and the reference area.

[0111] Optionally, for each registration area and the corresponding reference area in the reference fluorescence image, the computer device calculates the phase correlation between the registration area and the reference area, determines the pixel pair corresponding to the maximum phase correlation, and uses the deviation value between the pixel point of the registration area and the center pixel point in the pixel pair as the deviation value between the registration area and the reference area.

[0112] Optionally, after determining the central area correlation between the central registration area and the central reference area corresponding to the reference fluorescence image, it also includes: if the central area correlation is greater than a first correlation threshold, determining that the reference fluorescence image and the fluorescence image to be registered are successfully registered, and the registration result between the reference fluorescence image and the fluorescence image to be registered is the deviation value corresponding to the central area.

[0113] Step S206 : determining a registration result between the reference fluorescence image and the fluorescence image to be registered based on the deviation values ​​corresponding to the respective registration regions.

[0114] The registration result includes registration success and registration failure. If the registration is successful, the offset value (Offset) between the reference fluorescence image and the fluorescence image to be registered can be obtained.

[0115] It is understandable that after determining the reference fluorescence image, the computer device can more accurately register the fluorescence image to be registered with the reference fluorescence image based on the reference fluorescence image.

[0116] Furthermore, the fluorescence image to be registered includes at least two registration areas, and at least the two registration areas include a central registration area; the central area correlation between the central registration area and the central reference area corresponding to the reference fluorescence image is determined, and if the central area correlation is less than or equal to the first correlation threshold, the deviation value between each registration area and the corresponding reference area in the reference fluorescence image is obtained, then, based on the deviation value corresponding to each registration area, the problem of interference caused by using only one area for registration can be avoided, and the registration result between the reference fluorescence image and the fluorescence image to be registered can be determined more accurately, thereby improving the accuracy of fluorescence image registration. Furthermore, the computer device more accurately registers the reference fluorescence image and the fluorescence image to be registered, and can subsequently extract more correct cluster point (fluorescence point, cluster) information, thereby obtaining more accurate gene sequencing results.

[0117] In one embodiment, the fluorescence image to be registered includes at least three registration areas; based on the deviation values ​​corresponding to the respective registration areas, determining the registration result between the reference fluorescence image and the fluorescence image to be registered, including: subtracting the deviation values ​​corresponding to the respective registration areas in pairs to obtain at least two differences, and determining a target difference from the at least two differences; the target difference is less than a difference threshold; determining the registration area corresponding to the target difference, and using the registration area corresponding to the target difference as an element to constitute a region set; if there are at least two elements in the region set, determining the registration result between the reference fluorescence image and the fluorescence image to be registered based on the registration areas of the at least two elements.

[0118] The at least three registration areas include a central registration area and at least two non-central registration areas. The difference threshold can be set as required, such as a difference threshold of 1.0 pixel.

[0119] Optionally, the computer device obtains the deviation value corresponding to each registration area, subtracts each deviation value from each other to obtain at least two difference values, and determines a target difference value that is less than a difference threshold value from the at least two difference values.

[0120] Exemplarily, the fluorescence image to be registered includes 5 registration areas, and the computer device obtains the deviation value corresponding to each registration area, subtracts each deviation value from each other to obtain at least two differences, and determines a target difference value less than 1.0 pixel from the at least two differences; determines the registration area corresponding to the target difference value, and uses the registration area corresponding to the target difference value as an element to constitute a region set, that is, the elements in the region set are used as candidate values ​​to determine the registration result.

[0121] It can be understood that if there are at least two elements in the region set, it means that the deviation values ​​corresponding to the at least two elements are substantially the same, and the reference fluorescent image and the fluorescent image to be registered can be determined.

[0122] Optionally, if there are at least two elements in the region set, a second target registration region is determined from the at least two registration regions based on the correlation corresponding to each registration region; if the correlation of the second target registration region is greater than a third correlation threshold, it is determined that the reference fluorescence image and the fluorescence image to be registered are successfully registered, and the registration result between the reference fluorescence image and the fluorescence image to be registered is the deviation value corresponding to the second target registration region. The number of elements in the region set is positively correlated with the credibility of the image registration, that is, the more elements in the region set, the higher the credibility of the image registration.

[0123] Optionally, based on the registration areas of at least two elements, the registration result between the reference fluorescence image and the fluorescence image to be registered is determined, including: for the registration area of ​​each element, obtaining the correlation corresponding to each registration area; based on the correlation corresponding to the registration areas of at least two elements, determining a first target registration area from the registration areas of at least two elements; if the correlation of the first target registration area is greater than a second correlation threshold, it is determined that the reference fluorescence image and the fluorescence image to be registered are successfully registered, and the registration result between the reference fluorescence image and the fluorescence image to be registered is the deviation value corresponding to the first target registration area.

[0124] The second correlation threshold can be set as needed.

[0125] Optionally, the computer device determines a registration region with the greatest correlation from the registration regions of at least two elements as a first target registration region.

[0126] Optionally, the computer device determines a registration region with the second largest correlation from the registration regions of at least two elements as a first target registration region.

[0127] Optionally, the computer device may also determine the first target registration area in other ways, such as randomly determining the first target registration area from the registration areas of at least two elements, etc., which is not limited here.

[0128] Optionally, the above method also includes: if the correlation of the first target registration area is less than or equal to a second correlation threshold, then based on the correlation corresponding to each registration area, determining the second target registration area from at least two registration areas; if the correlation of the second target registration area is greater than a third correlation threshold, then determining that the baseline fluorescence image and the fluorescent image to be registered are successfully registered, and the registration result between the baseline fluorescence image and the fluorescent image to be registered is the deviation value corresponding to the second target registration area.

[0129] The third correlation threshold can be set as needed.

[0130] Optionally, the computer device determines a registration region with the greatest correlation from various registration regions as the second target registration region.

[0131] Optionally, the computer device determines a registration region with the second largest correlation from the registration regions of each element as a second target registration region.

[0132] Optionally, the computer device may also determine the second target registration area in other ways, such as randomly determining the second target registration area from various registration areas, etc., which is not limited here.

[0133] Optionally, if the correlation of the second target registration area is less than or equal to a third correlation threshold, it is determined that the registration of the reference fluorescent image and the fluorescent image to be registered has failed.

[0134] Optionally, if the correlation of the second target registration area is less than or equal to the third correlation threshold, at least 10 registration areas are randomly determined from the fluorescence image to be registered, and the step of determining the central area correlation between the central registration area and the central reference area corresponding to the reference fluorescence image is returned to execute the above-mentioned step to improve the success rate of registration between the reference fluorescence image and the fluorescence image to be registered; the 10 registration areas include the central registration area.

[0135] In this embodiment, the computer device subtracts the deviation values ​​corresponding to each registration area from each other to obtain at least two differences, and determines a target difference from the at least two differences, determines the registration area corresponding to the target difference, and uses the registration area corresponding to the target difference as an element to constitute a region set; then, if there are at least two elements in the region set, the registration result between the reference fluorescence image and the fluorescence image to be registered can be more accurately guaranteed.

[0136] Furthermore, the computer device determines a first target registration area from the registration areas of at least two elements based on the correlation corresponding to the registration areas of at least two elements; if the correlation of the first target registration area is greater than a second correlation threshold, it can be accurately determined that the baseline fluorescent image and the fluorescent image to be registered are successfully registered, and the registration result between the baseline fluorescent image and the fluorescent image to be registered is the deviation value corresponding to the first target registration area.

[0137] Furthermore, if the correlation of the first target registration area is less than or equal to the second correlation threshold, the computer device determines the second target registration area from at least two registration areas. If the correlation of the second target registration area is greater than the third correlation threshold, it can be accurately determined that the baseline fluorescence image and the fluorescent image to be registered are successfully registered, and the registration result between the baseline fluorescence image and the fluorescent image to be registered is the deviation value corresponding to the second target registration area.

[0138] In one embodiment, a method for determining the correlation between a registration area and a reference area corresponding to a reference fluorescence image includes: obtaining an initial correlation distribution map between the registration area and the reference area corresponding to the reference fluorescence image; determining a correlation area in the initial correlation distribution map with a peak extreme point in the initial correlation distribution map as the center; and determining the correlation between the registration area and the corresponding reference area based on the correlation area.

[0139] The position of the peak extreme point in the initial correlation distribution graph is the registration position. The correlation region is a region with the peak extreme point as the center, a side length of L, and an area of ​​LxL. Figure 6 Shown is a schematic diagram of the initial correlation distribution map.

[0140] Optionally, the computer device calculates an initial correlation distribution map between the registration area and the reference area corresponding to the reference fluorescence image through an image correlation matching algorithm. The image correlation matching algorithm includes template matching (spatial domain method), Fourier phase correlation matching (frequency domain method), etc., but is not limited thereto.

[0141] Optionally, based on the correlation area, the correlation between the registration area and the corresponding reference area is determined, including: obtaining a region matrix corresponding to the correlation area; determining the standard deviation, maximum value and minimum value of the region matrix; based on the standard deviation, maximum value and minimum value of the region matrix, determining the correlation between the registration area and the corresponding reference area.

[0142] Optionally, the computer device converts the correlation region into a region matrix, and determines the correlation between the registration region and the corresponding reference region based on the region matrix.

[0143] Optionally, the computer device determines a mean of the regional matrix and calculates a standard deviation based on the mean of the regional matrix.

[0144] Optionally, the computer device determines the correlation between the registration region and the corresponding reference region using the following formula: Relation = (Max-Min) / Std. Wherein, Relation is the correlation between the registration region and the corresponding reference region, Max is the maximum value of the region matrix, Min is the minimum value of the region matrix, and Std is the standard deviation of the region matrix.

[0145] It can be understood that the size of the correlation Relation between the registration region and the corresponding reference region is related to the size of the side length L of the correlation region, and the side length L of the correlation region is determined according to the standard deviation sigma of the peak curve. Figure 7 As shown in the figure, 4 to 6 times sigma is used to determine the side length L of the correlation region, for example, L = 6*sigma. Among them, Sigma is a measure of the width of the peak section, and the standard deviation Std of the area matrix is ​​a measure of the fluctuation of the signal height.

[0146] Relation is a multiple of std. When the peak of the peak extreme point in the initial correlation distribution graph is sharp, it will have little effect on the standard deviation std of the correlation area, but the ratio of (Max-Min) / std will become larger, that is, the correlation between the registration area and the corresponding reference area is stronger.

[0147] In this embodiment, the computer device obtains an initial correlation distribution map between the registration area and the reference area corresponding to the reference fluorescence image, and determines the correlation area in the initial correlation distribution map with the peak extreme point in the initial correlation distribution map as the center. Then, based on the correlation area, the correlation between the registration area and the corresponding reference area can be more accurately determined.

[0148] Furthermore, since the absolute value of the peak in the initial correlation distribution graph is related to the brightness of the image and the density of the cluster points, that is, when comparing different images, there may be a situation where the peak is high but the correlation is not high. For example, if the brightness of the two images is very high, the peak value (correlation) obtained may be relatively large, but if the two images are highly correlated but very dark, the peak value may be relatively small, that is, the correlation is more related to the sharpness of the peak (prominence). Therefore, the computer device obtains the regional matrix corresponding to the correlation area, and based on the standard deviation, maximum value and minimum value of the regional matrix, the correlation between the registration area and the corresponding reference area can be accurately determined, the interference caused by the changes in image brightness and cluster point density can be removed, and the correlation between the registration area and the reference area can be more accurately determined, so as to more accurately perform fluorescence image registration.

[0149] In one embodiment, another method for determining a reference fluorescent image is provided, which is applied to a computer device. The method for determining a reference fluorescent image includes the following steps:

[0150] Step A1, when the gene fragment reaction generates fluorescence, a fluorescence image sequence is obtained by photographing with a camera module of a sequencing instrument; the fluorescence image sequence includes at least two initial fluorescence images.

[0151] Step A2: down-sample the initial fluorescence image to obtain at least two candidate fluorescence images; the candidate fluorescence images include at least two regions.

[0152] Step A3: for each region in each candidate fluorescence image, extract pixel values ​​from the region and arrange the pixel values ​​into a one-dimensional vector.

[0153] Step A4, using a cosine correlation algorithm, determines the regional correlation between the one-dimensional vector of the region and the one-dimensional vectors of corresponding regions in other candidate fluorescence images.

[0154] Step A5, adding up the regional correlations corresponding to the region to obtain the target region correlation corresponding to the region.

[0155] Step A6, adding the target region correlation corresponding to each region in the candidate fluorescent image to obtain the target image correlation corresponding to the candidate fluorescent image.

[0156] Step A7, determining a reference fluorescent image from each candidate fluorescent image based on the target image correlation corresponding to each candidate fluorescent image.

[0157] Step A8: using the reference fluorescence image as a reference, registering the fluorescence image to be registered with the reference fluorescence image.

[0158] Wherein, step A8 includes steps A81 to A86:

[0159] Step A81, acquiring a reference fluorescent image and a fluorescent image to be registered; the fluorescent image to be registered includes at least two registration areas, the at least two registration areas include a central registration area and four non-central registration areas, and the four non-central registration areas are in different non-central positions.

[0160] Step A82, determine the central area correlation between the central registration area and the central reference area corresponding to the reference fluorescence image; if the central area correlation is greater than the first correlation threshold, it is determined that the reference fluorescence image and the fluorescence image to be registered are successfully registered, and the registration result between the reference fluorescence image and the fluorescence image to be registered is the deviation value corresponding to the central area; if the central area correlation is less than or equal to the first correlation threshold, execute steps A83 to A85.

[0161] Step A83, obtaining the deviation value between each registration area and the corresponding reference area in the reference fluorescence image; subtracting the deviation values ​​corresponding to each registration area in pairs to obtain at least two differences, and determining a target difference from the at least two differences; the target difference is less than the difference threshold; determining the registration area corresponding to the target difference, and using the registration area corresponding to the target difference as an element to constitute a region set.

[0162] Step A84: if there are at least two elements in the region set, for the registration region of each element, obtain the correlation corresponding to each registration region; based on the correlation corresponding to the registration regions of the at least two elements, determine a first target registration region from the registration regions of the at least two elements;

[0163] Step A85, if the correlation of the first target registration area is greater than the second correlation threshold, it is determined that the base fluorescence image and the fluorescence image to be registered are successfully registered, and the registration result between the base fluorescence image and the fluorescence image to be registered is the deviation value corresponding to the first target registration area; if the correlation of the first target registration area is less than or equal to the second correlation threshold, execute step A86.

[0164] Step A86, based on the correlation corresponding to each registration area, determine a second target registration area from at least two registration areas; if the correlation of the second target registration area is greater than a third correlation threshold, it is determined that the baseline fluorescence image and the fluorescence image to be registered are successfully registered, and the registration result between the baseline fluorescence image and the fluorescence image to be registered is the deviation value corresponding to the second target registration area.

[0165] Among them, the method for determining the correlation between the registration area and the reference area corresponding to the reference fluorescence image includes: obtaining an initial correlation distribution map between the registration area and the reference area corresponding to the reference fluorescence image; determining the correlation area in the initial correlation distribution map with the peak extreme point in the initial correlation distribution map as the center; obtaining a region matrix corresponding to the correlation area; determining the standard deviation, maximum value and minimum value of the region matrix; based on the standard deviation, maximum value and minimum value of the region matrix, determining the correlation between the registration area and the corresponding reference area.

[0166] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0167] Based on the same inventive concept, the embodiment of the present application also provides a device for determining a reference fluorescent image for implementing the method for determining a reference fluorescent image involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the method above, so the specific limitations in the embodiments of the device for determining one or more reference fluorescent images provided below can refer to the limitations of the method for determining a reference fluorescent image above, and will not be repeated here.

[0168] In an exemplary embodiment, Figure 8 As shown, a device for determining a reference fluorescent image is provided, comprising: a fluorescent image acquisition module 802, a region correlation determination module 804, an image correlation determination module 806 and a reference fluorescent image determination module 808, wherein:

[0169] The fluorescence image acquisition module 802 is used to acquire at least two candidate fluorescence images; the candidate fluorescence images include at least two regions.

[0170] The region correlation determination module 804 is used to determine, for each region in each candidate fluorescent image, the region correlation between the region and corresponding regions in other candidate fluorescent images, and determine the target region correlation corresponding to the region based on each of the region correlations.

[0171] The image correlation determination module 806 is used to determine the target image correlation corresponding to the candidate fluorescent image according to the target region correlation corresponding to each region in the candidate fluorescent image.

[0172] The reference fluorescent image determination module 808 is used to determine a reference fluorescent image from each candidate fluorescent image based on the target image correlation corresponding to each candidate fluorescent image.

[0173] The above-mentioned device for determining the reference fluorescent image obtains at least two candidate fluorescent images, and the candidate fluorescent images include at least two regions; for each region in each candidate fluorescent image, the regional correlation between the region and the corresponding region in other candidate fluorescent images is determined, and the target region correlation corresponding to the region is accurately determined based on the correlation of each region, and then the target image correlation corresponding to the candidate fluorescent image is accurately determined based on the target region correlation corresponding to each region in the candidate fluorescent image. Then, based on the target image correlation corresponding to each candidate fluorescent image, the reference fluorescent image can be accurately determined from each candidate fluorescent image.

[0174] In one embodiment, the region correlation determination module 804 is further configured to add up the region correlations corresponding to the region to obtain the target region correlation corresponding to the region.

[0175] In one embodiment, the image correlation determination module 806 is further configured to add the target region correlation corresponding to each region in the candidate fluorescent image to obtain the target image correlation corresponding to the candidate fluorescent image.

[0176] In one embodiment, the fluorescence image acquisition module 802 is also used to obtain a fluorescence image sequence by capturing it through a camera module of a sequencing instrument when the gene fragment reaction produces fluorescence; the fluorescence image sequence includes at least two initial fluorescence images; and the initial fluorescence image is downsampled to obtain at least two candidate fluorescence images.

[0177] In one embodiment, the above-mentioned regional correlation determination module 804 is also used to extract pixel values ​​from each region in each candidate fluorescence image, and arrange each pixel value into a one-dimensional vector; use a cosine correlation algorithm to determine the regional correlation between the one-dimensional vector of the region and the one-dimensional vector of the corresponding region in other candidate fluorescence images.

[0178] In one embodiment, the above-mentioned device further includes a fluorescence image registration module, which is used to register the fluorescence image to be registered with the reference fluorescence image based on the reference fluorescence image.

[0179] In one embodiment, the above-mentioned fluorescence image registration module is also used to determine the central area correlation between the central registration area and the central reference area corresponding to the reference fluorescence image; if the central area correlation is less than or equal to a first correlation threshold, then obtain the deviation value between each registration area and the corresponding reference area in the reference fluorescence image; based on the deviation values ​​corresponding to each registration area, determine the registration result between the reference fluorescence image and the fluorescence image to be registered.

[0180] The above-mentioned device for determining the reference fluorescent image obtains a reference fluorescent image and a fluorescent image to be registered, wherein the fluorescent image to be registered includes at least two registration areas, and the at least two registration areas include a central registration area; determines the central area correlation between the central registration area and the central reference area corresponding to the reference fluorescent image, and if the central area correlation is less than or equal to a first correlation threshold, obtains a deviation value between each registration area and the corresponding reference area in the reference fluorescent image. Then, based on the deviation values ​​corresponding to the respective registration areas, the problem of interference caused by using only one area for registration can be avoided, and the registration result between the reference fluorescent image and the fluorescent image to be registered can be determined more accurately, thereby improving the accuracy of fluorescence image registration.

[0181] In one embodiment, the fluorescence image to be registered includes at least three registration areas; the above-mentioned fluorescence image registration module is also used to subtract the deviation values ​​corresponding to each registration area from each other to obtain at least two differences, and determine a target difference from the at least two differences; the target difference is less than a difference threshold; determine the registration area corresponding to the target difference, and use the registration area corresponding to the target difference as an element to constitute a region set; if there are at least two elements in the region set, then based on the registration areas of the at least two elements, determine the registration result between the reference fluorescence image and the fluorescence image to be registered.

[0182] In one embodiment, the above-mentioned fluorescence image registration module is also used to obtain the correlation corresponding to each registration area of ​​each element; based on the correlation corresponding to the registration areas of at least two elements, determine a first target registration area from the registration areas of the at least two elements; if the correlation of the first target registration area is greater than a second correlation threshold, it is determined that the reference fluorescence image and the fluorescent image to be registered are successfully registered, and the registration result between the reference fluorescence image and the fluorescent image to be registered is the deviation value corresponding to the first target registration area.

[0183] In one embodiment, the above-mentioned fluorescence image registration module is also used to determine the second target registration area from the at least two registration areas based on the correlation corresponding to each registration area if the correlation of the first target registration area is less than or equal to a second correlation threshold; if the correlation of the second target registration area is greater than a third correlation threshold, it is determined that the reference fluorescence image and the fluorescent image to be registered are successfully registered, and the registration result between the reference fluorescence image and the fluorescent image to be registered is the deviation value corresponding to the second target registration area.

[0184] In one embodiment, the above-mentioned fluorescence image registration module is also used to determine that the registration of the reference fluorescence image and the fluorescence image to be registered is successful if the correlation of the central area is greater than a first correlation threshold, and the registration result between the reference fluorescence image and the fluorescence image to be registered is the deviation value corresponding to the central area.

[0185] In one embodiment, the at least two registration regions include a central registration region and four non-central registration regions, and the four non-central registration regions are located at different non-central positions.

[0186] In one embodiment, the above-mentioned fluorescence image registration module is also used to obtain an initial correlation distribution map between the registration area and the reference area corresponding to the reference fluorescence image; determine the correlation area in the initial correlation distribution map with the peak extreme point in the initial correlation distribution map as the center; based on the correlation area, determine the correlation between the registration area and the corresponding reference area.

[0187] In one embodiment, the above-mentioned fluorescence image registration module is also used to obtain the regional matrix corresponding to the correlation area; determine the standard deviation, maximum value and minimum value of the regional matrix; and determine the correlation between the registration area and the corresponding reference area based on the standard deviation, maximum value and minimum value of the regional matrix.

[0188] Each module in the above-mentioned device for determining the reference fluorescence image can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0189] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Fig. 9 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a method for determining a reference fluorescent image is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0190] Those skilled in the art will understand that Fig. 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0191] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0192] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0193] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0194] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0195] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0196] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0197] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for determining a reference fluorescence image, characterized in that: The method comprises: Acquire at least two candidate fluorescent images; the candidate fluorescent images include at least two regions; For each region in each candidate fluorescent image, determining a region correlation between the region and corresponding regions in other candidate fluorescent images, and determining a target region correlation corresponding to the region based on each of the region correlations; Determining a target image correlation corresponding to the candidate fluorescent image according to a target region correlation corresponding to each region in the candidate fluorescent image; Based on the target image correlation corresponding to each candidate fluorescent image, a reference fluorescent image is determined from each candidate fluorescent image.

2. The method according to claim 1, characterized in that The determining the target region correlation corresponding to the region based on the correlations of the respective regions includes: The region correlations corresponding to the regions are added together to obtain the target region correlation corresponding to the regions.

3. The method according to claim 1, characterized in that The step of determining the target image correlation corresponding to the candidate fluorescent image according to the target region correlation corresponding to each region in the candidate fluorescent image comprises: The target region correlation corresponding to each region in the candidate fluorescent image is added together to obtain the target image correlation corresponding to the candidate fluorescent image.

4. The method according to claim 1, characterized in that: The acquiring of at least two candidate fluorescence images comprises: When the gene fragments react to generate fluorescence, a fluorescence image sequence is obtained by photographing with a camera module of a sequencing instrument; the fluorescence image sequence includes at least two initial fluorescence images; The initial fluorescence image is downsampled to obtain at least two candidate fluorescence images.

5. The method according to claim 1, characterized in that The step of determining, for each region in each candidate fluorescent image, the region correlation between the region and corresponding regions in other candidate fluorescent images comprises: For each region in each candidate fluorescent image, extract pixel values ​​from the region and arrange the pixel values ​​into a one-dimensional vector; A cosine correlation algorithm is used to determine the regional correlation between the one-dimensional vector of the region and the one-dimensional vectors of corresponding regions in other candidate fluorescent images.

6. The method according to any one of claims 1 to 5, characterized in that: The method further comprises: The reference fluorescence image is used as a reference to register the fluorescence image to be registered with the reference fluorescence image.

7. A device for determining a reference fluorescent image, characterized in that: The device comprises: A fluorescence image acquisition module, used to acquire at least two candidate fluorescence images; the candidate fluorescence images include at least two areas; A region correlation determination module, used to determine, for each region in each candidate fluorescent image, a region correlation between the region and corresponding regions in other candidate fluorescent images, and determine a target region correlation corresponding to the region based on each of the region correlations; An image correlation determination module, used to determine the target image correlation corresponding to the candidate fluorescent image according to the target region correlation corresponding to each region in the candidate fluorescent image; The reference fluorescent image determination module is used to determine the reference fluorescent image from each candidate fluorescent image based on the target image correlation corresponding to each candidate fluorescent image.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

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

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images