Particle counting method, device, equipment and storage medium

Abstract

The present invention discloses a particle statistics method, device, equipment and storage medium. The method comprises: obtaining a bright field image corresponding to a current particle identification and a dark field image corresponding to the bright field image, the dark field image comprising at least two droplets, at least one of the at least two droplets comprising at least one particle corresponding to the current particle identification; determining parameter data of each droplet in the bright field image, determining parameter data of particles corresponding to the current particle identification in the dark field image, the parameter data comprising position range data; determining the statistical results of particles corresponding to the current particle identification according to the position range data of each droplet and the position range data of particles corresponding to the current particle identification. The technical effect of quickly and accurately determining the particle statistics results is achieved.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to a particle counting method, device, equipment and storage medium. Background Art

[0002] In single-cell multi-omics microfluidic experiments, particles of different colors usually represent different biological meanings. For particles of different colors, counting the number of droplets corresponding to different numbers of particles is very important for the subsequent evaluation of the interaction between particles and the control of microfluidic experiments.

[0003] Currently, for particles of each color, a user is required to manually determine the number of droplets of particles including each number of particles in the corresponding image.

[0004] In summary, existing particle statistical methods at least have the problem of low statistical efficiency. Summary of the invention

[0005] The present invention provides a particle counting method, device, equipment and storage medium to solve the problem of low statistical efficiency in existing particle counting methods.

[0006] According to one aspect of the present invention, there is provided a particle counting method, comprising:

[0007] Acquire a bright field image corresponding to a current particle identifier and a dark field image corresponding to the bright field image, wherein the dark field image includes at least two droplets, and at least one of the at least two droplets includes at least one particle corresponding to the current particle identifier;

[0008] Determining parameter data of each droplet in the bright field image, and determining parameter data of a particle corresponding to the current particle identifier in the dark field image, wherein the parameter data includes position range data;

[0009] The statistical result of the particles corresponding to the current particle identifier is determined according to the position range data of each droplet and the position range data of the particles corresponding to the current particle identifier.

[0010] Optionally, the statistical result includes the number of droplets enclosing a set number of particles of interest, where the particles of interest are particles corresponding to the current particle identifier.

[0011] Optionally, the step of acquiring a bright field image corresponding to the current particle identification and a dark field image corresponding to the bright field image includes:

[0012] In response to a particle statistics request, determining a particle identification sequence, wherein the particle identification sequence includes one particle identification, or at least two particle identifications arranged in sequence;

[0013] For each particle identification in the particle identification sequence, obtaining a bright field image corresponding to the current particle identification and a dark field image corresponding to the bright field image;

[0014] After determining the statistical result of the particle corresponding to the current particle identifier, the method further includes:

[0015] If the current particle identification is not the last particle identification in the particle identification sequence, the next particle identification in the particle identification sequence is used as the current particle identification, and the process returns to the step of obtaining a bright field image corresponding to the current particle identification and a dark field image corresponding to the bright field image.

[0016] Optionally, after determining the parameter data of the particle corresponding to the current particle identifier in the dark field image, the method further includes:

[0017] The position range data of particles that do not meet the corresponding particle size condition are deleted from the position range data of all particles corresponding to the current particle identification, so as to update the parameter data of the particles corresponding to the current particle identification.

[0018] Optionally, the parameter data of the droplet further includes a droplet identifier, and the parameter data of the particle further includes a sub-particle identifier, and the determining, based on the position range data of each droplet and the position range data of the particle corresponding to the current particle identifier, a statistical result of the particle corresponding to the current particle identifier includes:

[0019] According to the position range data of each droplet and the position range data of the particle corresponding to the current particle identifier, the sub-particle identifier of the particle wrapped by the droplet corresponding to each droplet identifier is determined:

[0020] According to the sub-particle identifiers of the particles wrapped by the droplets corresponding to the droplet identifiers, the statistical result of the particles corresponding to the current particle identifier is determined.

[0021] Optionally, the current particle identifier is a non-first particle identifier in the particle identifier sequence, the dark field image includes at least one particle corresponding to the current particle identifier and at least one particle corresponding to at least one other particle identifier, and the at least one other particle identifier is located before the current particle identifier in the particle identifier sequence;

[0022] The determining parameter data of particles corresponding to the current particle identifier in the dark field image includes:

[0023] Acquire position range data of at least one particle corresponding to the at least one other particle identifier, and use the position range corresponding to the position range data as a first position range;

[0024] Determine position range data of at least one target particle included in the dark field image, and use the position range corresponding to the position range data as a second position range;

[0025] For each target particle in the at least one target particle, if the second position range of the current target particle does not overlap with the second position range of at least one particle corresponding to the at least one other particle identifier, retaining the position range of the current target particle;

[0026] The retained position range data of all target particles are used as the position range data of particles corresponding to the current particle identifier in the dark field image.

[0027] Optionally, determining the position range data of at least one target particle included in the dark field image comprises:

[0028] Determining a grayscale image of the dark field image;

[0029] The grayscale image is input into a trained particle detection model to obtain parameter data of at least one target particle.

[0030] Optionally, it also includes:

[0031] The statistical results of the current particle identification are displayed in a visual interface.

[0032] Optionally, displaying the statistical result of the current particle identification in a visual interface includes:

[0033] The bar graph and / or line graph corresponding to the statistical results are displayed in the visual interface.

[0034] According to another aspect of the present invention, there is provided a particle counting device, comprising:

[0035] An image acquisition module, used to acquire a bright field image corresponding to a current particle identifier and a dark field image corresponding to the bright field image, wherein the dark field image includes at least two droplets, and at least one of the at least two droplets includes at least one particle corresponding to the current particle identifier;

[0036] a data determination module, configured to determine parameter data of each droplet in the bright field image, and parameter data of particles corresponding to the current particle identifier in the dark field image, wherein the parameter data includes position range data;

[0037] The result module is used to determine the statistical result of the particles corresponding to the current particle identifier according to the position range data of each droplet and the position range data of the particles corresponding to the current particle identifier.

[0038] According to another aspect of the present invention, a microfluidic device is provided, the microfluidic device comprising:

[0039] at least one processor; and

[0040] a memory communicatively connected to the at least one processor; wherein,

[0041] 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 perform the particle counting method described in any embodiment of the present invention.

[0042] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the particle statistics method described in any embodiment of the present invention when executed.

[0043] The technical solution of the particle counting method provided by the embodiment of the present invention determines the position range data of the droplets corresponding to the current particle identification based on the bright field image, thereby realizing the simple and accurate determination of the position range of each droplet; determines the position range data of each particle corresponding to the current particle identification based on the dark field image, thereby realizing the simple and accurate determination of the position range of each particle; determines the statistical result of the particles corresponding to the current particle identification according to the position range data of each droplet and the position range data of the particles corresponding to the current particle identification, thereby realizing the technical effect of determining the particles wrapped by the droplets by judging whether the particles are located in the coverage range of the droplets, and achieving the technical effect of simply and quickly determining the statistical result of the particles corresponding to the current particle identification.

[0044] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended 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

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0046] Figure 1 is a flow chart of a particle counting method provided according to an embodiment of the present invention;

[0047] Figure 2A is a bright field image corresponding to a single fluorescent dark field image provided by an embodiment of the present invention;

[0048] Figure 2B is a red fluorescent dark field image provided according to an embodiment of the present invention;

[0049] Figure 2C is a green fluorescent dark field image provided according to an embodiment of the present invention;

[0050] Figure 2D is a schematic diagram of an oil droplet capture cell provided according to an embodiment of the present invention;

[0051] Figure 3A is a bar graph corresponding to the statistical results of dead tumor cells provided by an embodiment of the present invention;

[0052] Figure 3B is a line graph corresponding to the statistical results of dead tumor cells provided by an embodiment of the present invention;

[0053] Figure 4 is a flow chart of a particle counting method provided according to an embodiment of the present invention;

[0054] Figure 5A is a bar graph corresponding to the total statistical results of two color particles provided by an embodiment of the present invention;

[0055] Figure 5B is a line graph corresponding to the total statistical results of two color particles provided by an embodiment of the present invention;

[0056] Figure 5C is a tumor lethality heat map provided according to an embodiment of the present invention;

[0057] Fig. 6A is a bar graph corresponding to the total statistical results of three color particles provided by an embodiment of the present invention;

[0058] Figure 6B is a line graph corresponding to the total statistical results of three color particles provided by an embodiment of the present invention;

[0059] Figure 7 is a flow chart of a particle counting method provided according to an embodiment of the present invention;

[0060] Figure 8 is a dark field image for identifying viable tumor cells (yellow particles) provided according to an embodiment of the present invention;

[0061] Fig. 9 is a dark field image for identifying viable T cells (green particles) provided according to an embodiment of the present invention;

[0062] Fig. 10A is a structural block diagram of a particle counting device provided according to an embodiment of the present invention;

[0063] Fig. 10B is a structural block diagram of a particle counting device provided according to an embodiment of the present invention;

[0064] Fig. 10C is a structural block diagram of a particle counting device provided according to an embodiment of the present invention;

[0065] Fig.11 This is the structure of the microfluidic device implementing the embodiment of the present invention. DETAILED DESCRIPTION

[0066] 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.

[0067] It should be noted that the terms "first", "second", 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 that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0068] Figure 1 A flow chart of a particle counting method is provided for an embodiment of the present invention. This embodiment can be applied to determine the statistical results of target particles in a microfluidic experiment. The method can be executed by a particle counting device. The particle counting device can be implemented in the form of hardware and / or software. The particle counting device can be configured in a processor. Figure 1 As shown, the method includes:

[0069] S110, acquiring a bright field image corresponding to a current particle identifier and a dark field image corresponding to the bright field image, wherein the dark field image includes at least two droplets, and at least one of the at least two droplets includes at least one particle corresponding to the current particle identifier.

[0070] Bright field images are images acquired when only the transmitted beam is allowed to pass through the objective lens aperture, see Figure 2AThe corresponding bright-field images of the single-fluorescence dark-field images are shown.

[0071] Dark field image is an image obtained by allowing only the set diffracted beam to pass through the objective aperture, see Figure 2B Red fluorescence dark field images shown, see Figure 2C The green fluorescence dark field image shown. Figure 2C The circular areas or approximate circular areas arranged in sequence are the position ranges of the droplets. Figure 2C and Figure 2B The clarity of the position range of each droplet in the dark field image may be different due to different excited fluorescence colors and / or different image acquisition parameters. For example, green fluorescence can improve the clarity of the position range of the droplet in the dark field image.

[0072] The dark field image corresponding to the bright field image refers to the dark field image of the field of view acquired under the imaging conditions of the dark field image before and after the bright field image is acquired. In this way, the bright field image and the dark field image approximately correspond to the same state of the microfluidic experiment. Among them, the droplets encapsulating the microparticles are located in the field of view.

[0073] Among them, the current particle identification varies with the content of the microfluidic experiment and the statistical object.

[0074] In one embodiment, Figure 2D As shown, taking the cell killing experiment as an example, a liquid containing surviving T cells is injected from the first branch channel 21 to the central channel 24, a liquid containing tumor cells is injected from the second branch channel 22 to the central channel 24, and a cell-wrapped droplet, such as an oil droplet, is injected from the third branch channel 23 to the central channel 24. The oil droplet continues to move after entering the central channel from the third branch channel, and captures tumor cells and / or T cells during the movement. As time goes by, the T cells in the droplets will gradually kill the tumor cells in the same droplet. In this process, most of the droplets include at least one of dead tumor cells, surviving tumor cells, surviving T cells and dead T cells. Among them, any marked cell can be used as a statistical object, such as a surviving T cell, a surviving tumor cell, a dead tumor cell or even a dead T cell. Therefore, the current particle identifier can be a particle identifier corresponding to any of the above cells. Among them, the marked cell refers to marking the cell to be counted by marking means such as fluorescent marking, and establishing a corresponding relationship between the cell to be counted and the marker, so that the number of corresponding cells can be counted by counting the number of markers.

[0075] In one embodiment, the dark field image includes at least one light spot corresponding to the current particle identifier, wherein one light spot corresponds to one particle. Unless otherwise specified, the light spots in the dark field image are referred to as particles in this embodiment.

[0076] S120, determining parameter data of each droplet in the bright field image, and determining parameter data of a particle corresponding to the current particle identifier in the dark field image, wherein the parameter data includes position range data.

[0077] Perform droplet identification on the bright field image to obtain parameter data of each droplet, wherein the parameter data at least includes position range data. In one embodiment, the parameter data includes droplet identification and position range data, wherein the position range data includes centroid and radius. Exemplary, {1, [A1, R1]; 2, [A2, R2]...}. Where 1 and 2 are droplet identifications; A1 and A2 are centroids; R1 and R2 are radii.

[0078] The dark field image is subjected to particle identification to obtain parameter data of the particle corresponding to the current particle identification, wherein the parameter data at least includes position range data. The position range data includes the center of mass and the radius. In one embodiment, the parameter data includes the sub-particle identification and position range data of the particle. Exemplarily, {1, [A 1, R 1]; 2, [A2, R2]...}. Among them, 1 and 2 are sub-particle identifications; A1 and A2 are the center of mass; R1 and R2 are the radii. Among them, the sub-particle identification is an identification used to represent each individual particle under the current particle identification.

[0079] In one embodiment, a grayscale image of a dark field image is determined; the grayscale image is input into a trained particle detection model to obtain parameter data of at least one target particle. Optionally, the particle detection model is a stardist model. This embodiment quickly and accurately completes particle recognition of the grayscale image through the particle detection model, thereby improving the accuracy and speed of particle recognition.

[0080] In one embodiment, after determining the parameter data of the particles corresponding to the current particle identifier in the dark field image, the position range data of the particles that do not meet the corresponding particle size conditions are deleted from the position range data of all particles corresponding to the current particle identifier, so as to update the parameter data of the particles corresponding to the current particle identifier. The particle size condition is related to the size of the particles corresponding to the current particle identifier. For example, for T cells, the particle size condition can be set to be greater than 20 pixels. This embodiment reduces the influence of noise on the accuracy of the particle identification processing results through the particle size condition, thereby improving the accuracy of the statistical results.

[0081] S130 , determining a statistical result of particles corresponding to the current particle identifier according to the position range data of each droplet and the position range data of particles corresponding to the current particle identifier.

[0082] In one embodiment, the statistical result includes the total number of particles corresponding to the current particle identifier.

[0083] In one embodiment, the statistical result includes the number of droplets encapsulating a set number of particles of interest, where the particles of interest are particles corresponding to the current particle identifier. For example, when the current particle identifier is a viable tumor cell, the statistical result may include: the number of droplets encapsulating one viable tumor cell, the number of droplets encapsulating two viable tumor cells, etc.

[0084] In one embodiment, the statistical results include an encapsulation rate. The encapsulation rate refers to the ratio of the number of droplets encapsulating viable T cells and viable tumor cells to the total number of droplets at time T0. Time T0 refers to the time when only viable T cells and viable tumor cells are included, that is, the time when tumor cells killed by T cells have not yet been generated.

[0085] It can be understood that if the position range corresponding to the position range data of a particle is within the position range corresponding to the position range data of any droplet, then the particle is wrapped in the droplet. Based on this, according to the position range data of each droplet and the position range data of the particle corresponding to the current particle identifier, the sub-particle identifier of the particle wrapped by the droplet corresponding to each droplet identifier can be determined, that is, the sub-particle identifier corresponding to each droplet identifier; after the sub-particle identifier corresponding to each droplet identifier is determined, the statistical result corresponding to the current particle identifier can be determined. Among them, one droplet identifier corresponds to one or more sub-particle identifiers.

[0086] In one embodiment, after the particle range data of each droplet and the position range data of each particle corresponding to the current particle identifier are determined, the droplet identifier corresponding to each particle is determined, that is, the droplet identifier corresponding to each sub-particle identifier is determined, and then at least one sub-particle identifier corresponding to each droplet identifier is determined based on the droplet identifier corresponding to each sub-particle identifier. One sub-particle identifier corresponds to one droplet identifier.

[0087] Regarding the statistical results, exemplarily, it includes the number of droplets corresponding to one particle with a current particle identifier, the number of droplets including particles corresponding to two current particle identifiers, etc. Exemplarily, {0:81, 1:49, 2:14, 3:6}, taking the current particle identifier as a surviving T cell as an example, the statistical result indicates that the number of droplets including 0 surviving T cells is 81, the number of droplets including 1 surviving T cell is 49, the number of droplets including 2 surviving T cells is 14, and the number of droplets including 3 surviving T cells is 6.

[0088] In one embodiment, after the statistical results are determined, the statistical results are displayed in a visual interface, such as a bar chart corresponding to the statistical results of dead tumor cells (see Figure 3A ), and / or, a line graph showing the statistical results of tumor cell death (see Figure 3B ).

[0089] The technical solution of the particle counting method provided by the embodiment of the present invention determines the position range data of the droplets corresponding to the current particle identification based on the bright field image, thereby realizing the simple and accurate determination of the position range of each droplet; determines the position range data of each particle corresponding to the current particle identification based on the dark field image, thereby realizing the simple and accurate determination of the position range of each particle; determines the statistical result of the particles corresponding to the current particle identification according to the position range data of each droplet and the position range data of the particles corresponding to the current particle identification, thereby realizing the technical effect of determining the particles wrapped by the droplets by judging whether the particles are located in the coverage range of the droplets, and achieving the technical effect of simply and quickly determining the statistical result of the particles corresponding to the current particle identification.

[0090] Figure 4 This is a flow chart of a particle counting method provided by an embodiment of the present invention, and this embodiment is used to refine the process of obtaining the bright field image and the dark field image corresponding to the current particle identification. Figure 4 As shown, the method includes:

[0091] S200: In response to a particle statistics request, determine a particle identification sequence, where the particle identification sequence includes one particle identification, or at least two particle identifications arranged in sequence.

[0092] In one embodiment, the user inputs the target particle identifier to be counted in the visual interface and then clicks the submit option. When the processor detects the submit operation, it generates a particle counting request. The particle counting request is parsed to obtain the target particle identifier, and the target particle identifier is used as the current particle identifier.

[0093] In one embodiment, the user selects the first particle identifier and the second particle identifier in the visual interface and clicks the confirmation option. When the processor detects the confirmation operation, it generates a particle statistics request and parses the particle statistics request to obtain a particle identifier sequence. The particle identifier sequence includes the first particle identifier and the second particle identifier. The order of the first particle identifier and the second particle identifier in the particle identifier sequence can be determined based on the selection order of the user when selecting the first particle identifier and the second particle identifier, or based on the default particle order.

[0094] S210 . For each particle identification in the particle identification sequence, obtain a bright field image corresponding to the current particle identification and a dark field image corresponding to the bright field image.

[0095] If the particle identification sequence includes only one particle identification, the particle identification is used as the current particle identification, and the bright field image corresponding to the current particle identification and the dark field image corresponding to the bright field image are obtained. If the particle identification sequence includes at least two particle identifications arranged in sequence, the corresponding particle identifications are used as the current particle identification in turn, and the bright field image corresponding to the current particle identification and the dark field image corresponding to the bright field image are obtained.

[0096] S220, determining parameter data of each droplet in the bright field image, and determining parameter data of a particle corresponding to the current particle identifier in the dark field image, wherein the parameter data includes position range data.

[0097] S230 , determining a statistical result of particles corresponding to the current particle identifier according to the position range data of each droplet and the position range data of particles corresponding to the current particle identifier.

[0098] S240: If the current particle identifier is not the last particle identifier in the particle identifier sequence, the next particle identifier in the particle identifier sequence is used as the current particle identifier, and the process returns to the step of obtaining a bright field image corresponding to the current particle identifier and a dark field image corresponding to the bright field image.

[0099] If the current particle identifier is not the last particle identifier in the particle identifier sequence, the next particle identifier in the particle identifier sequence is used as the current particle identifier, and the process of "obtaining a bright field image corresponding to the current particle identifier and a dark field image corresponding to the bright field image" in S220 is returned until the statistical result of the particles corresponding to the current particle identifier is obtained. If the current particle identifier is the last particle identifier in the particle identifier sequence, a prompt message indicating the end of particle statistics is output.

[0100] After the statistical results of the particles with all particle identifiers are determined, the total statistical results including the statistical results of all particle identifiers are output.

[0101] For example, the particle identification sequence is [dead tumor cells (red), living tumor cells (yellow)]. The overall statistical results are shown in the following table:

[0102] Table 1. Total statistical results of two color particles

[0103] Single droplet encapsulation volume Dead tumor cells (red) Surviving tumor cells (yellow) 0 219 202 1 48 65 2 19 16 3 5 7 4 2 1 5 0 2

[0104] The single droplet encapsulation amount in Table 1 indicates the number of corresponding cells encapsulated in a single droplet, such as the number of dead tumor cells encapsulated in the second column and the number of live tumor cells encapsulated in the third column. Specifically, for dead tumor cells, the number of droplets encapsulating 0 dead tumor cells is 219, the number of droplets encapsulating 1 dead tumor cell is 48, the number of droplets encapsulating 3 dead tumor cells is 5, and so on, the number of droplets encapsulating 4 and 5 dead tumor cells can be determined.

[0105] The corresponding bar graph of the total statistical results of the two color particles can be found in Figure 5A As shown, the line graph corresponding to the total statistical results of the two color particles can be found in Figure 5B shown.

[0106] In one embodiment, the statistical results include a kill rate. Figure 5C The killing rate heat map shown is used to describe the killing process of T cells on tumor cells. It can be seen from the killing rate heat map that when a single droplet contains 1 or 2 T cells, the killing effect of T cells in the droplet on tumor cells is significantly better than when the droplet contains multiple T cells. Therefore, the droplet containing 1 or 2 T cells is a more ideal droplet.

[0107] In another exemplary embodiment, the particle identification sequence is [dead tumor cells (red), living tumor cells (yellow), living T cells (green)]. The overall statistical results are shown in the following table:

[0108] Table 2 Total statistical results of three color particles

[0109] Single droplet encapsulation volume Dead tumor cells Surviving tumor cells Survival T cells 0 219 202 162 1 48 65 70 2 19 16 33 3 5 7 15 4 2 1 7 5 0 2 3 6 0 0 2 7 0 0 1

[0110] The corresponding bar graph of the total statistical results of the three color particles can be found in Fig. 6A As shown, the line graph corresponding to the total statistical results of the three color particles can be found in Figure 6B shown.

[0111] The embodiment of the present invention limits the particle identifications to be counted and the order between the particle identifications through the particle identification sequence; and sequentially determines the statistical results of the particles corresponding to the particle identifications in the particle identification sequence, which is simple, fast and efficient.

[0112] Figure 7A flowchart of a particle counting method provided in an embodiment of the present invention, this embodiment is used to refine the parameter data of particles corresponding to the current particle identifier based on the dark field image. This embodiment is suitable for the scenario of determining the parameter data of particles corresponding to the current particle identifier based on the dark field image of multiple fluorescent particles. The current particle identifier is a non-first particle identifier in the particle identifier sequence, and the dark field image includes at least one particle corresponding to the current particle identifier and at least one particle corresponding to at least one other particle identifier, and the at least one other particle identifier is located before the current particle identifier in the particle identifier sequence. Figure 7 As shown, the method includes:

[0113] S310, acquiring a bright field image corresponding to a current particle identifier and a dark field image corresponding to the bright field image, wherein the dark field image includes at least two droplets, and at least one of the at least two droplets includes at least one particle corresponding to the current particle identifier.

[0114] S3200, determining parameter data of each droplet in the bright field image.

[0115] S3201, obtaining position range data of at least one particle corresponding to the at least one other particle identifier, and taking the position range corresponding to the position range data as a first position range.

[0116] The other particle identifiers are different from the current particle identifier and are located before the current particle identifier in the particle identifier sequence.

[0117] Exemplarily, the particle identification sequence includes {dead tumor cells, live tumor cells, live T cells}. The dark field image used to identify live tumor cells (yellow particles) includes red particles (dead tumor cells, Figure 8 The dark spots in the image) and the yellow particles ( Figure 8 The current particle is marked as a living tumor cell (yellow), and the other particles are marked as dead tumor cells (red).

[0118] In another exemplary embodiment, the particle identification sequence includes {dead tumor cells, live tumor cells, live T cells}. The dark field image used to identify live T cells (green particles) includes red particles (dead tumor cells, Fig. 9 Medium dark spots), yellow particles (surviving tumor cells, Fig. 9 light spots in the middle) and green particles (surviving T cells, Fig. 9 The intermediate color spot in the image shows that the current particle is marked as a surviving T cell (green), and the other particles are marked as dead tumor markers (red) and surviving tumor cells (yellow).

[0119] It is understandable that, since other particle identifiers are located before the current particle identifier in the particle identifier sequence, the position range data of other particle identifiers have been determined. At this time, the position range data of at least one particle corresponding to the at least one other particle identifier can be directly read.

[0120] S3202: Determine position range data of at least one target particle included in the dark field image, and use the position range corresponding to the position range data as a second position range.

[0121] Since the dark field image includes the particle corresponding to the current particle identification and at least one particle corresponding to at least one other particle identification, the grayscale image corresponding to the dark field image also includes the particle corresponding to the current particle identification and at least one particle corresponding to at least one other particle identification. The grayscale image is input into the trained particle recognition model, and all particles in the grayscale image are identified to obtain the position range data of at least one target particle.

[0122] S3203: For each target particle in the at least one target particle, if the second position range of the current target particle does not overlap with the second position range of at least one particle corresponding to the at least one other particle identifier, retain the position range of the current target particle.

[0123] It can be understood that, since the position range data of the at least one target particle includes the position range data of the at least one particle corresponding to the at least one other particle identification, it is necessary to delete the position range of the at least one particle corresponding to the at least one other particle identification from the position range data of the at least one target particle. To this end, for each target particle, it is determined whether its second position range coincides with the first position range of the at least one particle corresponding to the at least one other particle identification. If they coincide, it means that the identification of the current target particle is not the current particle identification, but belongs to one of the at least one other particle identification, so the parameter data of the current target particle is deleted. If there is no coincidence, it means that the identification of the current target particle is the current particle identification, so the parameter data of the current target particle is retained.

[0124] This step deletes the position range data of at least one particle corresponding to the at least one other particle identification from the position range data of the at least one target particle through position range overlap judgment, thereby improving the accuracy of determining the position range data of at least one particle corresponding to the current particle identification, thereby improving the accuracy of the statistical results.

[0125] S3204: Using the retained position range data of all target particles as the position range data of each particle corresponding to the current particle identifier in the dark field image.

[0126] Since the retained position range data of the target particles are the position range data of the particles corresponding to the current particle identifier, the retained position range data of all target particles are used as the position range data of the particles corresponding to the current particle identifier in the dark field image.

[0127] S330 , determining the statistical result of the particles corresponding to the current particle identifier according to the position range data of each droplet and the position range data of the particles corresponding to the current particle identifier.

[0128] The embodiment of the present invention completes the operation of filtering the parameter data of the particles corresponding to the current particle identification from the position range data of the at least one target particle by retaining the parameter data of the target particles whose position range does not overlap with that of at least one particle corresponding to the at least one other particle identification, thereby achieving the technical effect of determining the parameter data of the particles corresponding to the current particle identification based on the multi-fluorescent particle dark field image with higher accuracy.

[0129] Fig. 10A A schematic diagram of the structure of a particle counting device provided in an embodiment of the present invention. Fig. 10A As shown, the device comprises:

[0130] An image acquisition module 101 is used to acquire a bright field image corresponding to a current particle identifier and a dark field image corresponding to the bright field image, wherein the dark field image includes at least two droplets, and at least one of the at least two droplets includes at least one particle corresponding to the current particle identifier;

[0131] A data determination module 102 is used to determine parameter data of each droplet in the bright field image, and determine parameter data of particles corresponding to the current particle identifier in the dark field image, wherein the parameter data includes position range data;

[0132] The result module 103 is used to determine the statistical result of the particles corresponding to the current particle identifier according to the position range data of each droplet and the position range data of the particles corresponding to the current particle identifier.

[0133] In one embodiment, the statistical result includes the number of droplets enclosing a set number of particles of interest, where the particles of interest are particles corresponding to the current particle identifier.

[0134] In one embodiment, the image acquisition module 101 is used to:

[0135] In response to a particle statistics request, determining a particle identification sequence, wherein the particle identification sequence includes one particle identification, or at least two particle identifications arranged in sequence;

[0136] For each particle identification in the particle identification sequence, obtaining a bright field image corresponding to the current particle identification and a dark field image corresponding to the bright field image;

[0137] After determining the statistical result of the particle corresponding to the current particle identifier, the method further includes:

[0138] If the current particle identification is not the last particle identification in the particle identification sequence, the next particle identification in the particle identification sequence is used as the current particle identification, and the process returns to the step of obtaining a bright field image corresponding to the current particle identification and a dark field image corresponding to the bright field image.

[0139] In one embodiment, Fig. 10B As shown, the device further includes an updating module 104, and the updating module 104 is used to:

[0140] The position range data of particles that do not meet the corresponding particle size condition are deleted from the position range data of all particles corresponding to the current particle identification, so as to update the parameter data of the particles corresponding to the current particle identification.

[0141] In one embodiment, the result module 103 is specifically used for:

[0142] According to the position range data of each droplet and the position range data of the particle corresponding to the current particle identifier, the sub-particle identifier of the particle wrapped by the droplet corresponding to each droplet identifier is determined:

[0143] According to the sub-particle identifiers of the particles wrapped by the droplets corresponding to the droplet identifiers, the statistical result of the particles corresponding to the current particle identifier is determined.

[0144] In one embodiment, the current particle identifier is a non-first particle identifier in the particle identifier sequence, the dark field image includes at least one particle corresponding to the current particle identifier and at least one particle corresponding to at least one other particle identifier, and the at least one other particle identifier is located before the current particle identifier in the particle identifier sequence; the data determination module 102 is specifically used to:

[0145] A data acquisition unit, configured to acquire position range data of at least one particle corresponding to the at least one other particle identifier, and use the position range corresponding to the position range data as a first position range;

[0146] A first position range data unit, used to determine position range data of at least one target particle included in the dark field image, and use the position range corresponding to the position range data as a second position range;

[0147] a retaining unit, configured to retain the position range of the current target particle for each target particle in the at least one target particle if the second position range of the current target particle does not overlap with the second position range of at least one particle corresponding to the at least one other particle identifier;

[0148] The second position range data unit is used to use the retained position range data of all target particles as the position range data of particles corresponding to the current particle identifier in the dark field image.

[0149] In one embodiment, the first location range data unit is specifically used for:

[0150] Determining a grayscale image of the dark field image;

[0151] The grayscale image is input into a trained particle detection model to obtain parameter data of at least one target particle.

[0152] In one embodiment, Fig. 10C As shown, the device further includes a display module 105, which is specifically used for:

[0153] The statistical results of the current particle identification are displayed in a visual interface.

[0154] In one embodiment, the display module 105 is specifically used for:

[0155] The bar graph and / or line graph corresponding to the statistical results are displayed in the visual interface.

[0156] The technical solution of the particle counting device provided by the embodiment of the present invention determines the position range data of the droplets corresponding to the current particle identification based on the bright field image, thereby realizing the simple and accurate determination of the position range of each droplet; determines the position range data of each particle corresponding to the current particle identification based on the dark field image, thereby realizing the simple and accurate determination of the position range of each particle; determines the statistical result of the particles corresponding to the current particle identification according to the position range data of each droplet and the position range data of the particles corresponding to the current particle identification, thereby realizing the technical effect of determining the particles wrapped by the droplets by judging whether the particles are located in the coverage range of the droplets, and achieving the technical effect of simply and quickly determining the statistical result of the particles corresponding to the current particle identification.

[0157] The particle counting device provided in the embodiment of the present invention can execute the particle counting method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0158] Fig.11The schematic diagram of the structure of the microfluidic device 10 that can be used to implement the embodiment of the present invention is shown. The microfluidic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11 in communication, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform 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 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the microfluidic 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. An input / output (I / O) interface 15 is also connected to the bus 14.

[0159] A number of components in the microfluidic 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 disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the microfluidic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0160] The processor 11 may be a variety of general and / or special 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 special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the particle statistics method.

[0161] In some embodiments, the particle statistics method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the microfluidic 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 particle statistics method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the particle statistics method in any other appropriate manner (e.g., by means of firmware).

[0162] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations 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 data and instructions to the storage system, the at least one input device, and the at least one output device.

[0163] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0164] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0165] To provide interaction with a user, the systems and techniques described herein can be implemented on a microfluidic 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 pointing device (e.g., a mouse or trackball) through which the user can provide input to the microfluidic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and the input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0166] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations 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 may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0167] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding 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 cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0168] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0169] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A particle counting method, characterized in that: include: Acquire a bright field image corresponding to a current particle identifier and a dark field image corresponding to the bright field image, wherein the dark field image includes at least two droplets, and at least one of the at least two droplets includes at least one particle corresponding to the current particle identifier; Determining parameter data of each droplet in the bright field image, and determining parameter data of a particle corresponding to the current particle identifier in the dark field image, wherein the parameter data includes position range data; The statistical result of the particles corresponding to the current particle identifier is determined according to the position range data of each droplet and the position range data of the particles corresponding to the current particle identifier.

2. The method according to claim 1, characterized in that The statistical result includes the number of droplets enclosing a set number of particles of interest, where the particles of interest are particles corresponding to the current particle identifier.

3. The method according to claim 1, characterized in that The step of acquiring a bright field image corresponding to the current particle identification and a dark field image corresponding to the bright field image includes: In response to a particle statistics request, determining a particle identification sequence, wherein the particle identification sequence includes one particle identification, or at least two particle identifications arranged in sequence; For each particle identification in the particle identification sequence, obtaining a bright field image corresponding to the current particle identification and a dark field image corresponding to the bright field image; After determining the statistical result of the particle corresponding to the current particle identifier, the method further includes: If the current particle identification is not the last particle identification in the particle identification sequence, the next particle identification in the particle identification sequence is used as the current particle identification, and the process returns to the step of obtaining a bright field image corresponding to the current particle identification and a dark field image corresponding to the bright field image.

4. The method according to claim 1, characterized in that: After determining the parameter data of the particle corresponding to the current particle identifier in the dark field image, the method further includes: The position range data of particles that do not meet the corresponding particle size condition are deleted from the position range data of all particles corresponding to the current particle identification, so as to update the parameter data of the particles corresponding to the current particle identification.

5. The method according to claim 1, characterized in that The parameter data of the droplet also includes a droplet identifier, and the parameter data of the particle also includes a sub-particle identifier. The determining of the statistical result of the particle corresponding to the current particle identifier according to the position range data of each droplet and the position range data of the particle corresponding to the current particle identifier includes: According to the position range data of each droplet and the position range data of the particle corresponding to the current particle identifier, the sub-particle identifier of the particle wrapped by the droplet corresponding to each droplet identifier is determined: According to the sub-particle identifiers of the particles wrapped by the droplets corresponding to the droplet identifiers, the statistical result of the particles corresponding to the current particle identifier is determined.

6. The method according to claim 1, characterized in that The current particle identifier is a non-first particle identifier in a particle identifier sequence, the dark field image includes at least one particle corresponding to the current particle identifier and at least one particle corresponding to at least one other particle identifier, and the at least one other particle identifier is located before the current particle identifier in the particle identifier sequence; The determining parameter data of particles corresponding to the current particle identifier in the dark field image includes: Acquire position range data of at least one particle corresponding to the at least one other particle identifier, and use the position range corresponding to the position range data as a first position range; Determine position range data of at least one target particle included in the dark field image, and use the position range corresponding to the position range data as a second position range; For each target particle in the at least one target particle, if the second position range of the current target particle does not overlap with the second position range of at least one particle corresponding to the at least one other particle identifier, retaining the position range of the current target particle; The retained position range data of all target particles are used as the position range data of particles corresponding to the current particle identifier in the dark field image.

7. The method according to claim 6, characterized in that The determining of the position range data of at least one target particle included in the dark field image comprises: Determining a grayscale image of the dark field image; The grayscale image is input into a trained particle detection model to obtain parameter data of at least one target particle.

8. The method according to any one of claims 1 to 7, characterized in that Also includes: The statistical results of the current particle identification are displayed in a visual interface.

9. The method according to claim 8, characterized in that The displaying of the statistical results of the current particle identification in the visual interface includes: The bar graph and / or line graph corresponding to the statistical results are displayed in the visual interface.

10. A particle counting device, characterized in that: include: An image acquisition module, used to acquire a bright field image corresponding to a current particle identifier and a dark field image corresponding to the bright field image, wherein the dark field image includes at least two droplets, and at least one of the at least two droplets includes at least one particle corresponding to the current particle identifier; a data determination module, configured to determine parameter data of each droplet in the bright field image, and parameter data of particles corresponding to the current particle identifier in the dark field image, wherein the parameter data includes position range data; The result module is used to determine the statistical result of the particles corresponding to the current particle identifier according to the position range data of each droplet and the position range data of the particles corresponding to the current particle identifier.

11. A microfluidic device, characterized in that: The microfluidic device comprises: 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 as to enable the at least one processor to perform the particle statistics method according to any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the particle statistics method according to any one of claims 1 to 9 when executed.

Images