Fluorescence amplification bright spot counting method, device, equipment and medium

Abstract

The invention discloses a fluorescent amplification bright spot counting method, device and equipment and a medium. The method comprises the following steps: acquiring a to-be-detected fluorescent bright spot image obtained by shooting nucleic acid amplification fluorescent bright spots in a hydrogel three-dimensional structure based on a high-depth-of-field camera; performing fluorescent bright spot identification on the to-be-detected fluorescent bright spot image to obtain a to-be-detected fluorescent signal area; determining a single fluorescent bright spot region and a fluorescent bright spot overlapping region from the to-be-detected fluorescent signal region, and determining the number of fluorescent bright spots contained in the fluorescent bright spot overlapping region; according to the number of the single fluorescent bright spot area and the number of fluorescent bright spots contained in the fluorescent bright spot overlapping area, fluorescent bright spot counting is carried out on the to-be-detected fluorescent bright spot image. According to the technical scheme, all fluorescence signals in the hydrogel three-dimensional structure can be captured through one-time imaging based on the high-depth-of-field camera, panoramic coverage of all layers is achieved, the layer out-of-focus problem can be effectively avoided, and the recognition efficiency and accuracy of fluorescent bright spots in the hydrogel three-dimensional structure can be improved.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to a method, device, equipment and medium for counting fluorescence amplification bright spots. Background Art

[0002] Nucleic acid amplification and quantification has always been one of the core technologies in the field of molecular biology. It has been applied to research fields such as molecular sequencing, gene expression analysis, gene mutation research, early molecular diagnosis of diseases, single nucleotide polymorphisms and drug screening, and plays an important role.

[0003] In nucleic acid amplification and quantification, an important problem that needs to be solved is to achieve the capture and accurate counting of fluorescent amplification bright spots. In related technologies, traditional microscopes are used to image nucleic acid amplification fluorescent bright spots in hydrogel three-dimensional structures. However, in order to detect fluorescent bright spots at different depths (i.e., layers), multiple translations and shots are required during the imaging process, which makes the sample imaging time longer. At the same time, there is a problem of layer defocus, which leads to inaccurate identification of fluorescent bright spots. Summary of the invention

[0004] The present invention provides a method, device, equipment and medium for counting fluorescent amplification bright spots. Based on a high depth of field camera, all fluorescent signals in a hydrogel three-dimensional structure can be captured through one imaging, thereby achieving panoramic coverage of all layers, effectively avoiding the problem of layer defocusing, and helping to improve the recognition efficiency and accuracy of nucleic acid amplification fluorescent bright spots in the hydrogel three-dimensional structure.

[0005] According to one aspect of the present invention, a method for counting fluorescent amplification bright spots is provided, the method comprising:

[0006] Acquire a fluorescent bright spot image to be tested, wherein the fluorescent bright spot image to be tested is obtained by photographing the fluorescent bright spots of nucleic acid amplification in the three-dimensional structure of the hydrogel with a high depth of field camera, wherein the high depth of field camera is a camera with a depth of field range greater than a preset range;

[0007] Performing fluorescent bright spot recognition on the fluorescent bright spot image to be tested to obtain a fluorescent signal area to be tested;

[0008] Determine a single fluorescent bright spot area and a fluorescent bright spot overlapping area from the fluorescent signal area to be detected, and determine the number of fluorescent bright spots contained in the fluorescent bright spot overlapping area;

[0009] According to the number of the single fluorescent bright spot areas and the number of fluorescent bright spots contained in the fluorescent bright spot overlapping area, the fluorescent bright spot count is performed on the fluorescent bright spot image to be tested.

[0010] According to another aspect of the present invention, a device for counting fluorescent amplification bright spots is provided, the device comprising:

[0011] A fluorescence bright spot image acquisition module, configured to acquire a fluorescence bright spot image to be measured, where the fluorescence bright spot image to be measured is obtained based on a nucleic acid amplification fluorescence bright spot in a three-dimensional structure of a hydrogel captured by a high-depth-of-field camera, and the high-depth-of-field camera is a camera with a depth of field greater than a preset range;

[0012] A fluorescence signal region determination module, configured to perform fluorescence bright spot recognition on the fluorescence bright spot image to be measured to obtain a fluorescence signal region to be measured;

[0013] A fluorescence bright spot overlapping region determination module, configured to determine a single fluorescence bright spot region and a fluorescence bright spot overlapping region from the fluorescence signal region to be measured, and determine the number of fluorescence bright spots included in the fluorescence bright spot overlapping region;

[0014] A fluorescence bright spot counting module, configured to perform fluorescence bright spot counting on the fluorescence bright spot image to be measured according to the number of the single fluorescence bright spot regions and the number of fluorescence bright spots included in the fluorescence bright spot overlapping region.

[0015] According to another aspect of the present invention, an electronic device is provided, and the electronic device includes:

[0016] At least one processor; and,

[0017] A memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program executable by the at least one processor, and when the computer program is executed by the at least one processor, the at least one processor is enabled to execute the fluorescence amplification bright spot counting method according to any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, and the computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, the fluorescence amplification bright spot counting method according to any embodiment of the present invention is implemented.

[0020] In the technical solution of the embodiment of the present invention, a to-be-detected fluorescent bright spot image is obtained. The to-be-detected fluorescent bright spot image is obtained based on a high-depth-of-field camera photographing nucleic acid amplification fluorescent bright spots in a hydrogel three-dimensional structure. The high-depth-of-field camera is a camera with a depth of field range greater than a preset range. The to-be-detected fluorescent bright spot image is subjected to fluorescent bright spot recognition to obtain a to-be-detected fluorescent signal region. A single fluorescent bright spot region and a fluorescent bright spot overlapping region are determined from the to-be-detected fluorescent signal region, and the number of fluorescent bright spots included in the fluorescent bright spot overlapping region is determined. According to the number of single fluorescent bright spot regions and the number of fluorescent bright spots included in the fluorescent bright spot overlapping region, fluorescent bright spot counting is performed on the to-be-detected fluorescent bright spot image. In this technical solution, all fluorescent signals in the hydrogel three-dimensional structure can be captured through one imaging based on the high-depth-of-field camera, achieving panoramic coverage of all layers, effectively avoiding the problem of layer defocus, and helping to improve the recognition efficiency and accuracy of nucleic acid amplification fluorescent bright spots in the hydrogel three-dimensional structure.

[0021] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0023] Figure 1 is a flowchart of a method for counting fluorescent amplification bright spots according to Embodiment 1 of the present invention;

[0024] Figure 2 is an optical path diagram of high-depth-of-field imaging according to Embodiment 1 of the present invention;

[0025] Figure 3 is a flowchart of a method for counting fluorescent amplification bright spots according to Embodiment 2 of the present invention;

[0026] Figure 4 is a schematic structural diagram of a device for counting fluorescent amplification bright spots according to Embodiment 3 of the present invention;

[0027] Figure 5 is a schematic structural diagram of an electronic device for implementing the method for counting fluorescent amplification bright spots of the embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0028] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first", "second", "target", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] Embodiment 1

[0031] Figure 1 This is a flow chart of a method for counting fluorescent amplification bright spots provided in Example 1 of the present invention. This embodiment is applicable to the case of quickly and accurately counting nucleic acid amplification bright spots in a hydrogel three-dimensional structure. The method can be performed by a counting device for fluorescent amplification bright spots. The counting device for fluorescent amplification bright spots can be implemented in the form of hardware and / or software. The counting device for fluorescent amplification bright spots can be configured in an electronic device with data processing capabilities. Figure 1 As shown, the method includes:

[0032] S110, obtaining a fluorescent bright spot image to be tested, wherein the fluorescent bright spot image to be tested is obtained based on photographing the fluorescent bright spots of nucleic acid amplification in the three-dimensional structure of the hydrogel by a high depth of field camera, wherein the high depth of field camera is a camera with a depth of field range greater than a preset range.

[0033] Among them, the hydrogel three-dimensional structure may refer to a three-dimensional hydrogel nucleic acid amplification reaction system, which can use the inherent porous structure of the hydrogel to uniformly confine the target nucleic acid molecules in the sample to be tested in the pores, and perform nucleic acid amplification and fluorescence imaging on the entire reaction system. The preset range may refer to a preset reference depth of field range of a high depth of field camera. It should be noted that the high depth of field camera needs to be able to meet the imaging depth requirements of the hydrogel three-dimensional structure, that is, the one-time imaging of the high depth of field camera can directly capture the fluorescence signals at different depths in the hydrogel three-dimensional structure.

[0034] Figure 2 This is an optical path diagram for high-depth-of-field imaging provided by Embodiment 1 of the present invention. As Figure 2 shown, the high-depth-of-field imaging optical path includes a high-depth-of-field camera (Camera), a tube lens (Tube Len), a filter (Filter), an objective lens (ObjectiveLen), a sample (Sample), and a laser (Laser).

[0035] In this embodiment, based on the high-depth-of-field camera, fluorescence bright spots at different depths in the three-dimensional structure of the hydrogel are photographed to obtain an image of the fluorescence bright spots to be measured. The image of the fluorescence bright spots to be measured contains multiple pixel points, and the pixel value corresponding to each pixel point represents the light intensity. Fluorescence imaging is performed using the high-depth-of-field camera, so that all the fluorescence bright spots in the entire three-dimensional structure of the hydrogel can be clearly imaged at one time, thus effectively avoiding the problems of long imaging time and layer defocus caused by multiple movements and shootings of the three-dimensional structure of the hydrogel in traditional microscopic imaging.

[0036] S120. Identify the fluorescence bright spots in the image of the fluorescence bright spots to be measured to obtain the region of the fluorescence signal to be measured.

[0037] In this embodiment, after obtaining the image of the fluorescence bright spots to be measured, the fluorescence bright spots in the image of the fluorescence bright spots to be measured can be identified to obtain the region of the fluorescence signal to be measured. Among them, the region of the fluorescence signal to be measured may refer to the detection region including the fluorescence signal. Exemplarily, the shape of the region of the fluorescence signal to be measured may be a rectangle or a square, etc. This embodiment does not make specific limitations and can be flexibly set according to actual detection requirements.

[0038] In this embodiment, optionally, identifying the fluorescence bright spots in the image of the fluorescence bright spots to be measured to obtain the region of the fluorescence signal to be measured includes: inputting the image of the fluorescence bright spots to be measured into the fluorescence bright spot recognition model, and determining the region of the fluorescence signal to be measured according to the output result of the fluorescence bright spot recognition model; wherein, the fluorescence bright spot recognition model is a machine learning model pre-trained for realizing image fluorescence bright spot recognition.

[0039] Specifically, the fluorescent bright spot recognition model is pre-trained to learn the features (such as brightness and shape, etc.) of fluorescent signals and interference signals (such as reflective signals and impurities, etc.). Exemplarily, the fluorescent bright spot recognition model can be a YOLO (You Only LookOnce) model, such as a YOLOv8 model. The trained fluorescent bright spot recognition model can be used to identify each signal point in the fluorescent bright spot image to be tested to obtain multiple signal point areas, and classify each signal point area to output a classification result, which includes the signal point area and its category (fluorescent signal or interference signal). According to the characteristics of the fluorescent signal, the fluorescent bright spot recognition model can automatically distinguish between fluorescent signals and interference signals. In this way, multiple fluorescent signal areas to be tested can be quickly and accurately identified from the fluorescent bright spot image to be tested, thereby effectively avoiding interference signals from affecting the accuracy of fluorescent bright spot counting.

[0040] Through such a setting, this scheme combines high depth of field imaging and machine learning models to achieve fully automated recognition and counting of three-dimensional fluorescent bright spots.

[0041] S130, determining a single fluorescent bright spot area and a fluorescent bright spot overlapping area from the fluorescent signal area to be detected, and determining the number of fluorescent bright spots contained in the fluorescent bright spot overlapping area.

[0042] Among them, a single fluorescent bright spot area may refer to a detection area containing only one fluorescent bright spot. The fluorescent bright spot overlapping area may refer to a detection area containing multiple fluorescent bright spots. It should be noted that due to the one-time imaging of the hydrogel three-dimensional structure by a high depth of field camera, the nucleic acid amplification fluorescent bright spots of different imaging depths may overlap. If the number of fluorescent signal areas to be tested is directly used as the counting result of nucleic acid amplification fluorescent bright spots at this time, the counting result will be inaccurate. Therefore, in order to ensure the counting accuracy of nucleic acid amplification fluorescent bright spots, it is necessary to determine whether there is an overlapping fluorescent bright spot area in the fluorescent signal area to be tested, and count the fluorescent bright spots based on the determination result.

[0043] In this embodiment, optionally, a single fluorescent bright spot area and a fluorescent bright spot overlapping area are determined from the fluorescent signal area to be tested, including: determining an intensity difference matrix corresponding to the fluorescent signal area to be tested; wherein the intensity difference matrix is used to describe the light intensity changes between adjacent pixels in the fluorescent signal area to be tested; and determining a single fluorescent bright spot area and a fluorescent bright spot overlapping area from the fluorescent signal area to be tested according to the intensity difference matrix and a preset intensity difference threshold; wherein the preset intensity difference threshold is set based on the gain and exposure time of the high depth of field camera and the external ambient light.

[0044] Specifically, first, determine the intensity difference matrix corresponding to the fluorescence signal region to be measured (which can be used to describe the change in light intensity between adjacent pixels within the fluorescence signal region to be measured). Optionally, determining the intensity difference matrix corresponding to the fluorescence signal region to be measured includes: taking the difference between the light intensities of adjacent pixels within the fluorescence signal region to be measured to obtain candidate light intensity differences; and determining the intensity difference matrix corresponding to the fluorescence signal region to be measured based on the candidate light intensity differences.

[0045] Exemplarily, the candidate light intensity differences of the fluorescence signal region to be measured can be calculated according to the formula D i,j =|I i,j -I i+1,j |. Wherein, I i,j represents the pixel intensity of the fluorescence bright spot image to be measured at (i,j). Then, arrange the candidate light intensity differences in order to obtain the intensity difference matrix corresponding to the fluorescence signal region to be measured.

[0046] After determining the intensity difference matrix corresponding to the fluorescence signal region to be measured, the single fluorescence bright spot region and the fluorescence bright spot overlapping region can be determined from the fluorescence signal region to be measured according to the intensity difference matrix and the preset intensity difference threshold. Among them, the preset intensity difference threshold can be an intensity difference reference value preset based on the gain and exposure time of the high-depth camera and the external ambient light, and can be used as the discrimination basis for the single fluorescence bright spot region and the fluorescence bright spot overlapping region.

[0047] In this embodiment, optionally, determining the single fluorescence bright spot region and the fluorescence bright spot overlapping region from the fluorescence signal region to be measured according to the intensity difference matrix and the preset intensity difference threshold includes: determining whether there is a candidate light intensity difference in the intensity difference matrix that is greater than the preset intensity difference threshold; if so, determining the fluorescence signal region corresponding to the intensity difference matrix as the fluorescence bright spot overlapping region; otherwise, determining the fluorescence signal region corresponding to the intensity difference matrix as the single fluorescence bright spot region.

[0048] Exemplarily, assuming that the preset intensity difference threshold is represented as T D , if there is D i,j >T D in a certain fluorescence signal region to be measured, it can be considered that there are multiple fluorescence bright spots in this fluorescence signal region to be measured. At this time, this fluorescence signal region to be measured can be determined as the fluorescence bright spot overlapping region; otherwise, it indicates that there is only one fluorescence bright spot in this fluorescence signal region to be measured. At this time, this fluorescence signal region to be measured can be determined as the single fluorescence bright spot region.

[0049] Through such a setting, this solution introduces a differential analysis method based on the fluorescence signal intensity to solve the problem of counting deviation caused by the superposition of fluorescence bright spot signals in three-dimensional imaging.

[0050] After determining the single fluorescent bright spot region and the overlapping region of fluorescent bright spots, the number of fluorescent bright spots included in the overlapping region of fluorescent bright spots can be further determined. Optionally, determining the number of fluorescent bright spots included in the overlapping region of fluorescent bright spots includes: determining a reference average intensity based on the average intensity of a single fluorescent bright spot region; determining the number of fluorescent bright spots included in the overlapping region of fluorescent bright spots according to the ratio of the average intensity of the overlapping region of fluorescent bright spots to the reference average intensity.

[0051] Specifically, first based on the formula calculate the total intensity of each single fluorescent bright spot region respectively. Among them, I i represents the intensity of the i-th pixel in the single fluorescent bright spot region, and N represents the number of pixels in the single fluorescent bright spot region. Then for each single fluorescent bright spot region, according to the formula calculate the average intensity of the single fluorescent bright spot region, and then average the average intensities of each single fluorescent bright spot region to obtain the reference average intensity I single . Then calculate the average intensity I x of each overlapping region of fluorescent bright spots based on the above formula, and according to the formula the number of fluorescent bright spots included in the overlapping region of fluorescent bright spots can be determined. Exemplarily, assume that I x ≈2·I single , that is, n≈2, then it can be determined that the number of fluorescent bright spots included in this overlapping region of fluorescent bright spots is 2; if I x ≈3·I single , that is, n≈3, then it can be determined that the number of fluorescent bright spots included in this overlapping region of fluorescent bright spots is 3. Among them, the approximate relationship can be judged according to the principle of rounding.

[0052] With such a setting in this solution, by detecting the intensity distribution of fluorescent bright spots, the overlapping region of fluorescent bright spots can be accurately identified and the number of overlapping fluorescent bright spots can be inferred, thus providing a technical guarantee for the absolute quantification of three-dimensional fluorescence signals.

[0053] S140, perform fluorescent bright spot counting on the fluorescent bright spot image to be measured according to the number of single fluorescent bright spot regions and the number of fluorescent bright spots included in the overlapping region of fluorescent bright spots.

[0054] Specifically, add the number of single fluorescent bright spot regions (one single fluorescent bright spot region contains one fluorescent bright spot) and the number of fluorescent bright spots included in the overlapping region of fluorescent bright spots, and use the sum result as the number of fluorescent bright spots corresponding to the fluorescent bright spot image to be measured.

[0055] The technical solution of the embodiment of the present invention is to obtain an image of a fluorescent bright spot to be measured, where the image of the fluorescent bright spot to be measured is obtained by a high-depth-of-field camera photographing the nucleic acid amplification fluorescent bright spot in the three-dimensional structure of the hydrogel, and the high-depth-of-field camera is a camera with a depth-of-field range greater than a preset range; perform fluorescent bright spot recognition on the image of the fluorescent bright spot to be measured to obtain a region of the fluorescent signal to be measured; determine a single fluorescent bright spot region and a fluorescent bright spot overlapping region from the region of the fluorescent signal to be measured, and determine the number of fluorescent bright spots included in the fluorescent bright spot overlapping region; perform fluorescent bright spot counting on the image of the fluorescent bright spot to be measured according to the number of single fluorescent bright spot regions and the number of fluorescent bright spots included in the fluorescent bright spot overlapping region. In this technical solution, all fluorescent signals in the three-dimensional structure of the hydrogel can be captured through a single imaging based on the high-depth-of-field camera, achieving panoramic coverage of all layers, effectively avoiding the problem of layer defocus, and helping to improve the recognition efficiency and accuracy of nucleic acid amplification fluorescent bright spots in the three-dimensional structure of the hydrogel.

[0056] Embodiment 2

[0057] Figure 3 The flowchart of a method for counting fluorescent amplification bright spots provided by Embodiment 2 of the present invention is based on the above embodiment for optimization. Specifically, the optimization is as follows: after obtaining the image of the fluorescent bright spot to be measured, it further includes: performing smoothing processing on the image of the fluorescent bright spot to be measured, and updating the image of the fluorescent bright spot to be measured based on the result of the smoothing processing.

[0058] As Figure 3 shown, the method of this embodiment specifically includes the following steps:

[0059] S210, obtain an image of a fluorescent bright spot to be measured, where the image of the fluorescent bright spot to be measured is obtained by a high-depth-of-field camera photographing the nucleic acid amplification fluorescent bright spot in the three-dimensional structure of the hydrogel, and the high-depth-of-field camera is a camera with a depth-of-field range greater than a preset range.

[0060] S220, perform smoothing processing on the image of the fluorescent bright spot to be measured, and update the image of the fluorescent bright spot to be measured based on the result of the smoothing processing.

[0061] Exemplarily, the image of the fluorescent bright spot to be measured can be smoothed by Gaussian filtering to reduce the interference of background noise. Among them, the pixel value of the filtered image can smooth the background through the following formula: G(x,y) represents the pixel value after filtering, and σ controls the degree of smoothing.

[0062] S230, perform fluorescent bright spot recognition on the updated image of the fluorescent bright spot to be measured to obtain a region of the fluorescent signal to be measured.

[0063] S240, determine a single fluorescent bright spot region and a fluorescent bright spot overlapping region from the region of the fluorescent signal to be measured, and determine the number of fluorescent bright spots included in the fluorescent bright spot overlapping region.

[0064] S250 counts the fluorescent bright spots in the fluorescent bright spot image to be measured according to the number of single fluorescent bright spot regions and the number of fluorescent bright spots included in the overlapping region of fluorescent bright spots.

[0065] Among them, the specific implementation manners of S230 - S250 can refer to the relevant descriptions in the above - mentioned embodiments, and will not be elaborated here.

[0066] In the technical solution of the embodiment of the present invention, after obtaining the fluorescent bright spot image to be measured, the fluorescent bright spot image to be measured is also subjected to smoothing processing, the fluorescent bright spot image to be measured is updated based on the smoothing processing result, and then the recognition and counting of fluorescent bright spots are performed based on the updated fluorescent bright spot image to be measured. This technical solution can effectively reduce the interference of background noise through image smoothing processing, which helps to improve the counting accuracy of fluorescent bright spots in the fluorescent bright spot image to be measured.

[0067] Embodiment III

[0068] Figure 4 FIG. is a schematic structural diagram of a counting device for fluorescent amplification bright spots provided by Embodiment III of the present invention. This device can execute the counting method for fluorescent amplification bright spots provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method. As Figure 4 shown, the device includes:

[0069] A fluorescent bright spot image acquisition module 310, configured to acquire a fluorescent bright spot image to be measured, where the fluorescent bright spot image to be measured is obtained by a high - depth - of - field camera photographing nucleic acid amplification fluorescent bright spots in a hydrogel three - dimensional structure, and the high - depth - of - field camera is a camera with a depth - of - field range greater than a preset range;

[0070] A fluorescent signal region determination module 320, configured to perform fluorescent bright spot recognition on the fluorescent bright spot image to be measured to obtain a to - be - measured fluorescent signal region;

[0071] A fluorescent bright spot overlapping region determination module 330, configured to determine single fluorescent bright spot regions and fluorescent bright spot overlapping regions from the to - be - measured fluorescent signal region, and determine the number of fluorescent bright spots included in the fluorescent bright spot overlapping region;

[0072] A fluorescent bright spot counting module 340, configured to count the fluorescent bright spots in the fluorescent bright spot image to be measured according to the number of the single fluorescent bright spot regions and the number of fluorescent bright spots included in the fluorescent bright spot overlapping region.

[0073] Optionally, the fluorescent signal region determination module 320 is specifically configured to:

[0074] Input the fluorescent bright spot image to be measured into a fluorescent bright spot recognition model, and determine the to - be - measured fluorescent signal region according to the output result of the fluorescent bright spot recognition model;

[0075] Among them, the fluorescence bright spot recognition model is a machine learning model pre-trained for realizing the recognition of fluorescence bright spots in images.

[0076] Optionally, the fluorescence bright spot overlapping region determination module 330 includes:

[0077] An intensity difference matrix determination unit, configured to determine an intensity difference matrix corresponding to the to-be-detected fluorescence signal region; wherein, the intensity difference matrix is used to describe the light intensity change between adjacent pixels in the to-be-detected fluorescence signal region;

[0078] A fluorescence bright spot overlapping region determination unit, configured to determine a single fluorescence bright spot region and a fluorescence bright spot overlapping region from the to-be-detected fluorescence signal region according to the intensity difference matrix and a preset intensity difference threshold; wherein, the preset intensity difference threshold is set based on the gain and exposure time of the high-depth camera and the external ambient light.

[0079] Optionally, the intensity difference matrix determination unit is specifically configured to:

[0080] Subtract the light intensities of adjacent pixels in the to-be-detected fluorescence signal region to obtain candidate light intensity differences;

[0081] Determine the intensity difference matrix corresponding to the to-be-detected fluorescence signal region according to the candidate light intensity differences.

[0082] Optionally, the fluorescence bright spot overlapping region determination unit is specifically configured to:

[0083] Determine whether there is a candidate light intensity difference in the intensity difference matrix that is greater than the preset intensity difference threshold;

[0084] If so, determine the to-be-detected fluorescence signal region corresponding to the intensity difference matrix as the fluorescence bright spot overlapping region;

[0085] Otherwise, determine the to-be-detected fluorescence signal region corresponding to the intensity difference matrix as a single fluorescence bright spot region.

[0086] Optionally, the fluorescence bright spot overlapping region determination module 330 is configured to:

[0087] Determine a reference average light intensity according to the average light intensity of the single fluorescence bright spot region;

[0088] Determine the number of fluorescence bright spots included in the fluorescence bright spot overlapping region according to the ratio of the average light intensity of the fluorescence bright spot overlapping region to the reference average light intensity.

[0089] Optionally, the device further includes: an image smoothing processing module, configured to:

[0090] After obtaining the image of the fluorescence bright spot to be measured, perform smoothing processing on the image of the fluorescence bright spot to be measured, and update the image of the fluorescence bright spot to be measured based on the result of the smoothing processing.

[0091] The fluorescence amplification bright spot counting device provided by the embodiment of the present invention can execute the fluorescence amplification bright spot counting method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method.

[0092] Embodiment 4

[0093] Figure 5 The structural schematic diagram of the electronic device 10 that can be used to implement the embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as, laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, personal digital processors, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are only examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0094] As Figure 5 shown, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. Among them, the memory stores a computer program executable by the at least one processor. The processor 11 can execute various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0095] A plurality of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disc, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0096] The processor 11 may be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the method for counting fluorescence amplification bright spots.

[0097] In some embodiments, the method for counting fluorescence amplification bright spots can be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for counting fluorescence amplification bright spots described above can be executed. Alternatively, in other embodiments, the processor 11 can be configured to execute the method for counting fluorescence amplification bright spots by any other suitable means (e.g., by means of firmware).

[0098] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuitry, integrated circuit systems, field-programmable gate arrays (FPGA), application-specific integrated circuits (ASIC), application-specific standard products (ASSP), systems-on-chip (SOC), complex programmable logic devices (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special-purpose or general-purpose programmable processor, that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0099] The computer programs for implementing the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to the processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer programs are executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer programs can be executed entirely on the machine, partially on the machine, as a stand-alone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0100] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0101] To provide for interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can also be used to provide for interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0102] The systems and techniques described herein can be implemented in a computing system that includes backend components (such as, for example, a data server), or a computing system that includes middleware components (such as, for example, an application server), or a computing system that includes frontend components (such as, for example, a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (such as, for example, a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.

[0103] A computing system may include a client and a server. The client and the server are generally far from each other and usually interact via a communication network. The relationship between the client and the server is created by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, solving the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0104] It should be understood that various forms of processes shown above can be used, steps can be reordered, added or deleted. For example, the steps described in the present invention can be executed in parallel, sequentially or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is made herein.

[0105] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for counting fluorescent amplification highlights, characterized in that, The method includes: Obtaining a fluorescence bright spot image to be measured, where the fluorescence bright spot image to be measured is obtained based on a nucleic acid amplification fluorescence bright spot in a three-dimensional structure of a hydrogel captured by a high-depth-of-field camera, and the high-depth-of-field camera is a camera with a depth-of-field range greater than a preset range; Performing fluorescence bright spot recognition on the fluorescence bright spot image to be measured to obtain a fluorescence signal region to be measured; Determining a single fluorescence bright spot region and a fluorescence bright spot overlapping region from the fluorescence signal region to be measured, and determining the number of fluorescence bright spots included in the fluorescence bright spot overlapping region; Performing fluorescence bright spot counting on the fluorescence bright spot image to be measured according to the number of single fluorescence bright spot regions and the number of fluorescence bright spots included in the fluorescence bright spot overlapping region.

2. The method according to claim 1, wherein Performing fluorescence bright spot recognition on the fluorescence bright spot image to be measured to obtain a fluorescence signal region to be measured, including: Inputting the fluorescence bright spot image to be measured into a fluorescence bright spot recognition model, and determining the fluorescence signal region to be measured according to the output result of the fluorescence bright spot recognition model; Wherein, the fluorescence bright spot recognition model is a machine learning model pre-trained for realizing image fluorescence bright spot recognition.

3. The method according to claim 1, wherein Determining a single fluorescence bright spot region and a fluorescence bright spot overlapping region from the fluorescence signal region to be measured, including: Determining an intensity difference matrix corresponding to the fluorescence signal region to be measured; wherein, the intensity difference matrix is used to describe the light intensity change between adjacent pixels in the fluorescence signal region to be measured; Determining a single fluorescence bright spot region and a fluorescence bright spot overlapping region from the fluorescence signal region to be measured according to the intensity difference matrix and a preset intensity difference threshold; wherein, the preset intensity difference threshold is set based on the gain and exposure time of the high-depth-of-field camera and external ambient light.

4. The method according to claim 3, wherein Determining an intensity difference matrix corresponding to the fluorescence signal region to be measured, including: Subtracting the light intensity of adjacent pixels in the fluorescence signal region to be measured to obtain a candidate light intensity difference; Determining the intensity difference matrix corresponding to the fluorescence signal region to be measured according to the candidate light intensity difference.

5. The method according to claim 4, characterized in that, Determining a single fluorescence bright spot region and a fluorescence bright spot overlapping region from the fluorescence signal region to be measured according to the intensity difference matrix and a preset intensity difference threshold, including: Determining whether there is a candidate light intensity difference greater than the preset intensity difference threshold in the intensity difference matrix; If so, determining the fluorescence signal region corresponding to the intensity difference matrix as the fluorescence bright spot overlapping region; Otherwise, determining the fluorescence signal region corresponding to the intensity difference matrix as a single fluorescence bright spot region.

6. The method according to claim 5, characterized in that, Determining the number of fluorescence bright spots included in the fluorescence bright spot overlapping region, including: Determining a reference average light intensity according to the average light intensity of the single fluorescence bright spot region; Determining the number of fluorescence bright spots included in the fluorescence bright spot overlapping region according to the ratio of the average light intensity of the fluorescence bright spot overlapping region to the reference average light intensity.

7. The method according to any one of claims 1-6, characterized in that, After obtaining the fluorescence bright spot image to be measured, the method further includes: Performing smoothing processing on the fluorescence bright spot image to be measured, and updating the fluorescence bright spot image to be measured based on the smoothing processing result.

8. A counting device for fluorescent amplification highlights, characterized in that The device includes: A fluorescence bright spot image acquisition module, configured to acquire a fluorescence bright spot image to be measured, where the fluorescence bright spot image to be measured is obtained based on a nucleic acid amplification fluorescence bright spot in a three-dimensional structure of a hydrogel captured by a high-depth-of-field camera, and the high-depth-of-field camera is a camera with a depth-of-field range greater than a preset range; A fluorescence signal region determination module, configured to perform fluorescence bright spot recognition on the fluorescence bright spot image to be measured to obtain a fluorescence signal region to be measured; A fluorescence bright spot overlapping region determination module, configured to determine a single fluorescence bright spot region and a fluorescence bright spot overlapping region from the fluorescence signal region to be measured, and determine the number of fluorescence bright spots included in the fluorescence bright spot overlapping region; A fluorescence bright spot counting module, configured to perform fluorescence bright spot counting on the fluorescence bright spot image to be measured according to the number of single fluorescence bright spot regions and the number of fluorescence bright spots included in the fluorescence bright spot overlapping region.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the fluorescence amplification bright spot counting method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions, and the computer instructions are used to implement the fluorescence amplification bright spot counting method according to any one of claims 1-7 when executed by a processor.

Images