Sample cell control system and sample imaging method

Abstract

The invention discloses a sample cell control system and a sample imaging method, and the system comprises a fixed frame which is used for placing a sample cell; the first transmission assembly comprises a first transmission shaft, a first transmission part and a first transmission rod, the first transmission shaft is arranged in the x-axis direction, and the first transmission part moves along the first transmission shaft so that the first transmission part can drive the fixing frame to move along the x-axis through the first transmission rod; the second transmission assembly comprises a second transmission shaft, a second transmission piece and a second transmission rod, and the second transmission piece moves along the second transmission shaft so that the second transmission piece can drive the fixing frame to move along the y axis through the second transmission rod; the control device controls the first transmission shaft to drive the first transmission part to move or / and controls the second transmission shaft to drive the second transmission part to move. According to the invention, the sample cell can be controlled to move along the x axis or the y axis, and multi-position flexible movement of the sample cell can be realized.

Description

Technical Field

[0001] The invention relates to the technical field of microscope imaging, and in particular to a sample pool control system and a sample imaging method. Background Art

[0002] With the continuous development of scientific research, especially in the fields of life sciences, physical chemistry, and nanotechnology, fluorescence microscopy has become an important tool for observing microstructures and their dynamic behaviors. In order to capture the dynamic behavior of these tiny structures, multi-region, high-precision imaging is a common requirement in experiments. In existing fluorescence microscopes, manual operation is relied upon to adjust the position of the sample pool, which is not only time-consuming and laborious, but also prone to positioning deviations, affecting the accuracy and repeatability of experimental results. In addition, the movement of the sample pool is limited to the adjustment of a single position, and it is impossible to achieve flexible movement of the sample pool in multiple positions, resulting in low efficiency for experimenters when observing and analyzing complex samples. This limitation is particularly prominent in tasks that require efficient imaging of multiple regions. Summary of the invention

[0003] The object of the present invention is to provide a sample pool control system and a sample imaging method, which can control the movement of the sample pool and realize the flexible movement of the sample pool in multiple positions.

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] A sample pool control system, comprising:

[0006] A fixed frame for placing the sample pool;

[0007] A first transmission assembly comprises a first transmission shaft, a first transmission member and a first transmission rod, wherein the first transmission shaft is arranged along the x-axis direction, the first transmission member is connected to the first transmission shaft, one end of the first transmission rod is connected to the first transmission member, and the other end is connected to the fixed frame, and the first transmission shaft is used to drive the first transmission member to move along the first transmission shaft, so that the first transmission member drives the fixed frame to move along the x-axis through the first transmission rod;

[0008] A second transmission assembly includes a second transmission shaft, a second transmission member and a second transmission rod, wherein the second transmission shaft is arranged along the y-axis direction, the second transmission member is connected to the second transmission shaft, one end of the second transmission rod is connected to the second transmission member, and the other end is connected to the fixed frame, and the second transmission shaft is used to drive the second transmission member to move along the second transmission shaft, so that the second transmission member drives the fixed frame to move along the y-axis through the second transmission rod;

[0009] A control device is connected to the first transmission assembly and the second transmission assembly, respectively, and is used to transmit control signals to the first transmission assembly and the second transmission assembly, respectively, so as to control the first transmission shaft to drive the first transmission member to move and / or control the second transmission shaft to drive the second transmission member to move.

[0010] Optionally, the fixed frame is provided with a fixed ring, the sample pool is placed in the fixed ring, the fixed ring is provided with a rotating part, the first end and the second end of the fixed ring are respectively connected to the periphery of the rotating part, so that the rotating part rotates to change the diameter of the fixed ring.

[0011] Optionally, the first transmission assembly further comprises a first driving assembly connected to the first transmission shaft, and configured to drive the first transmission shaft to rotate, so that the first transmission shaft drives the first transmission member to move along the first transmission shaft;

[0012] The second transmission assembly also includes a second drive assembly connected to the second transmission shaft, which is used to drive the second transmission shaft to rotate, so that the second transmission shaft drives the second transmission member to move along the second transmission shaft.

[0013] Optionally, the first transmission assembly further includes a first guide rail arranged along the x-axis direction, for supporting the first transmission member and guiding the first transmission member to move;

[0014] The second transmission assembly also includes a second guide rail arranged along the y-axis direction, which is used to support the second transmission member and guide the second transmission member to move.

[0015] A sample imaging method, wherein a sample pool is placed on a fixed frame, a first transmission assembly and a second transmission assembly are respectively connected to the fixed frame, the first transmission assembly is used to drive the fixed frame to move along the x-axis, and the second transmission assembly is used to drive the fixed frame to move along the y-axis; the sample imaging method comprises:

[0016] The sample pool is moved to an initial position by the first transmission assembly and the second transmission assembly, and an imaging device is controlled to acquire an image of the sample in the sample pool to obtain an image;

[0017] Detecting a light spot in the image, and determining a target area of ​​the image according to the light spot characteristics;

[0018] A moving path is planned according to the initial position and the position of the target area of ​​the image, so that the sample pool is moved to the target position through the first transmission component and the second transmission component according to the moving path, so that the imaging device acquires an image of the sample in the sample pool when the sample pool moves to the target position.

[0019] Optionally, detecting a light spot in the image, and determining a target area of ​​the image according to a feature of the light spot includes:

[0020] Performing a multi-layer convolution operation on the image to extract features at different levels from the image;

[0021] Generating a plurality of candidate detection frames in the image according to the features, and obtaining positions, categories, and confidences of the candidate detection frames;

[0022] The target detection frame is screened out according to the confidence level of the candidate detection frame, so as to determine the target area according to the target detection frame.

[0023] Optionally, detecting a light spot in the image, and determining a target area of ​​the image according to a feature of the light spot includes:

[0024] Extracting features from the image, generating a plurality of target detection frames in the image according to the features, wherein the target detection frames are used to frame the light spots, and the area framed by the target detection frames in the image is the detection area;

[0025] Extracting features from the shallow layer to the deep layer of the detection area layer by layer, combining the features of each layer to obtain a feature vector, wherein the feature vector includes light spot information;

[0026] The detection area whose spot information meets the requirements is screened out as the target area.

[0027] Optionally, determining the target area of ​​the image according to the light spot feature includes:

[0028] Extracting features from the image, generating a plurality of target detection frames in the image according to the features, wherein the target detection frames are used to frame the light spots, and the area framed by the target detection frames in the image is the detection area;

[0029] Obtaining the light spot intensity of the detection area, dividing the detection area into a plurality of blocks, obtaining the light spot intensity of any one of the plurality of blocks, and obtaining the light spot distribution uniformity of the detection area according to the light spot intensity of the plurality of blocks;

[0030] According to the light spot intensity and / or the light spot distribution uniformity of each of the detection areas, the detection areas whose light spot intensity and / or the light spot distribution uniformity meet the requirements are screened out as the target areas.

[0031] Optionally, planning a moving path according to the initial position and the position of the target area of ​​the image includes:

[0032] Determining the target position according to the position of the target area of ​​the image;

[0033] Update the closed list, the open list and the current node in sequence for multiple times. In any update, add the current node to the closed list, add the adjacent nodes of the current node to the open list, and find the node with the smallest total cost from the open list as the current node in the next update, until the current node is the target position, then stop updating. In the first update, the initial position is used as the current node. The total cost describes the sum of the distance traveled from the initial position to the corresponding position of the node and the distance required to travel from the corresponding position of the node to the target position.

[0034] The moving path is obtained according to each node in the closed list.

[0035] Optionally, detecting a light spot in the image, and determining a target area of ​​the image according to the light spot characteristics comprises: determining first to Mth target areas of the image according to the light spot characteristics, where M is a positive integer greater than or equal to 2;

[0036] Planning a moving path according to the initial position and the position of the target area of ​​the image includes:

[0037] The first to M-th sub-movement paths are planned sequentially, wherein the first sub-movement path is planned according to the initial position and the position of the first target area, the first target area is the target area with the smallest distance from the corresponding position in the first to M-th target areas to the initial position, and the m-th sub-movement path is planned according to the position of the m-1-th target area and the position of the m-th target area, the m-th target area is the target area with the smallest distance from the position in the remaining target areas to the position of the m-1-th target area, m∈[2,M];

[0038] According to the moving path, moving the sample pool to a target position by the first transmission assembly and the second transmission assembly includes:

[0039] According to the first to Mth sub-moving paths, the sample pool is moved by the first transmission component and the second transmission component in sequence, so that the sample pool is moved to the first to Mth target positions in sequence, and the first to Mth target positions are the sample pool positions corresponding to the first to Mth target areas in sequence.

[0040] It can be known from the above technical scheme that a sample pool control system provided by the present invention includes: a fixed frame for placing the sample pool; a first transmission assembly, including a first transmission shaft, a first transmission member and a first transmission rod, the first transmission shaft is arranged along the x-axis direction, the first transmission member is connected to the first transmission shaft, one end of the first transmission rod is connected to the first transmission member, and the other end is connected to the fixed frame, the first transmission shaft is used to drive the first transmission member to move along the first transmission shaft, so that the first transmission member drives the fixed frame to move along the x-axis through the first transmission rod; a second transmission assembly, including a second transmission shaft, a second transmission member and a second transmission rod, the second transmission shaft is arranged along the y-axis direction, the second transmission member is connected to the second transmission shaft, one end of the second transmission rod is connected to the second transmission member, and the other end is connected to the fixed frame, the second transmission shaft is used to drive the second transmission member to move along the second transmission shaft, so that the second transmission member drives the fixed frame to move along the y-axis through the second transmission rod; a control device is connected to the first transmission assembly and the second transmission assembly respectively, and is used to transmit control signals to the first transmission assembly and the second transmission assembly respectively, so as to control the first transmission shaft to drive the first transmission member to move or / and control the second transmission shaft to drive the second transmission member to move. The sample pool control system of the present invention can control the movement of the sample pool, can control the movement of the sample pool along the x-axis or along the y-axis, and can realize the flexible movement of the sample pool in multiple positions.

[0041] A sample imaging method provided by the present invention can control the movement of a sample pool to achieve imaging of the sample. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. 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 paying creative work.

[0043] Figure 1 A schematic diagram of a sample pool control system provided by one embodiment of the present invention;

[0044] Figure 2-1 A side view showing the connection between a fixed ring and a rotating member of a sample pool control system provided by one embodiment of the present invention;

[0045] Figure 2-2 A top view of a fixed ring and a rotating member of a sample pool control system provided by one embodiment of the present invention;

[0046] Figure 3 A flow chart of a sample imaging method provided by one embodiment of the present invention;

[0047] Figure 4A specific flow chart of a sample imaging method provided by one embodiment of the present invention;

[0048] Figure 5 A flow chart of a method for detecting a target in an image in a sample imaging method provided by an embodiment of the present invention;

[0049] Figure 6 A flow chart of a method for extracting features from a detection area and screening a target area in a sample imaging method provided in one embodiment of the present invention;

[0050] Figure 7 A flow chart of a method for planning a moving path of a sample imaging method provided in one embodiment of the present invention.

[0051] The reference numerals in the drawings of the specification include:

[0052] 1-fixed frame, 2-sample pool, 11-fixed ring, 12-rotating part, 5-imaging device, 41-first motor, 42-second motor, 43-first transmission shaft, 44-second transmission shaft, 45-first transmission member, 46-second transmission member, 47-first guide rail, 48-second guide rail, 49-first coupling, 50-second coupling, 51-first transmission rod, 52-second transmission rod, 6-control device, 61-cable. DETAILED DESCRIPTION

[0053] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the technical solutions 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.

[0054] This embodiment provides a sample pool control system, including:

[0055] A fixed frame for placing the sample pool;

[0056] A first transmission assembly comprises a first transmission shaft, a first transmission member and a first transmission rod, wherein the first transmission shaft is arranged along the x-axis direction, the first transmission member is connected to the first transmission shaft, one end of the first transmission rod is connected to the first transmission member, and the other end is connected to the fixed frame, and the first transmission shaft is used to drive the first transmission member to move along the first transmission shaft, so that the first transmission member drives the fixed frame to move along the x-axis through the first transmission rod;

[0057] A second transmission assembly includes a second transmission shaft, a second transmission member and a second transmission rod, wherein the second transmission shaft is arranged along the y-axis direction, the second transmission member is connected to the second transmission shaft, one end of the second transmission rod is connected to the second transmission member, and the other end is connected to the fixed frame, and the second transmission shaft is used to drive the second transmission member to move along the second transmission shaft, so that the second transmission member drives the fixed frame to move along the y-axis through the second transmission rod;

[0058] A control device is connected to the first transmission assembly and the second transmission assembly, respectively, and is used to transmit control signals to the first transmission assembly and the second transmission assembly, respectively, so as to control the first transmission shaft to drive the first transmission member to move and / or control the second transmission shaft to drive the second transmission member to move.

[0059] The control device transmits a control signal to the first transmission assembly, and can control the first transmission shaft to drive the first transmission member to move along the first transmission shaft, so that the first transmission member drives the fixed frame to move along the x-axis through the first transmission rod, thereby controlling the sample pool to move along the x-axis. The control device transmits a control signal to the second transmission assembly, and can control the second transmission shaft to drive the second transmission member to move along the second transmission shaft, so that the second transmission member drives the fixed frame to move along the y-axis through the second transmission rod, thereby controlling the sample pool to move along the y-axis. Therefore, the sample pool control system of this embodiment can control the movement of the sample pool, can control the movement of the sample pool along the x-axis or along the y-axis, and can realize flexible movement of the sample pool in multiple positions.

[0060] For example, reference may be made to Figure 1 , Figure 1 A schematic diagram of a sample pool control system provided by an embodiment, as shown in the figure, the sample pool 2 is placed on the fixed frame 1, the first transmission shaft 43 is arranged along the x-axis direction, the first transmission member 45 is connected to the first transmission shaft 43, one end of the first transmission rod 51 is connected to the first transmission member 45, and the other end is connected to the fixed frame 1, the second transmission shaft 44 is arranged along the y-axis direction, the second transmission member 46 is connected to the second transmission shaft 44, one end of the second transmission rod 52 is connected to the second transmission member 46, and the other end is connected to the fixed frame 1. The control device 6 is connected to the first transmission assembly and the second transmission assembly respectively.

[0061] In some embodiments, the fixed frame 1 is provided with a fixed ring 11, and the sample pool 2 is placed in the fixed ring 11, so as to fix the sample pool 2 and ensure that it remains stable during the transmission process. In some embodiments, the diameter of the fixed ring 11 is adjustable to meet the needs of sample pools of different sizes. In some embodiments, the fixed ring 11 is provided with a rotating member 12, and the first end and the second end of the fixed ring 11 are respectively connected to the periphery of the rotating member 12, so that the rotating member 12 rotates to change the diameter of the fixed ring 11. For sample pools 2 of different sizes, after placing the sample pool 2 in the fixed ring 11, the rotating member 12 can be rotated so that the first end and the second end of the fixed ring 11 revolve around the periphery of the rotating member 12, so that the fixed ring 11 is tightened or loosened to adapt to sample pools 2 of different sizes. The rotating member 12 can be but is not limited to a gear.

[0062] For example, reference may be made to Figure 2-1 and Figure 2-2 , Figure 2-1 A side view of the connection between a fixed ring and a rotating member of a sample pool control system provided by an embodiment, Figure 2-2 This is a top view of a fixed ring and a rotating member of a sample pool control system provided by an embodiment, and the curve with an arrow indicates the rotation direction of the rotating member 12. As shown in the figure, the first end and the second end of the fixed ring 11 are respectively connected to the periphery of the rotating member 12, and the diameter of the fixed ring 11 can be changed by rotating the rotating member 12.

[0063] In some embodiments, the first transmission shaft 43 may rotate about its own axis, and drive the first transmission member 45 to move along the first transmission shaft 43, and the rotational motion is converted into linear motion through the first transmission shaft 43 and the first transmission member 45. In some embodiments, the first transmission assembly may further include a first drive assembly connected to the first transmission shaft 43, used to drive the first transmission shaft 43 to rotate, so that the first transmission shaft 43 drives the first transmission member 45 to move along the first transmission shaft 43. In some embodiments, the first drive assembly may include a first motor 41 and a first coupling 49, the first motor 41 is connected to the first transmission shaft 43 through the first coupling 49, and the first motor 41 drives the first transmission shaft 43 to rotate through the first coupling 49. In some embodiments, the first transmission assembly may further include a first guide rail 47 arranged along the x-axis direction, the first guide rail 47 is used to support the first transmission member 45 and guide the first transmission member 45 to move, so that the first transmission member 45 can stably move along the first transmission shaft 43, and prevent the first transmission member 45 from tilting or overturning. The first guide rail 47 can be arranged in parallel with the first transmission shaft 43 and is a linear guide rail.

[0064] In some embodiments, the second transmission shaft 44 may rotate about its own axis, and drive the second transmission member 46 to move along the second transmission shaft 44, and the rotational motion is converted into linear motion through the second transmission shaft 44 and the second transmission member 46. In some embodiments, the second transmission assembly may further include a second drive assembly connected to the second transmission shaft 44, used to drive the second transmission shaft 44 to rotate, so that the second transmission shaft 44 drives the second transmission member 46 to move along the second transmission shaft 44. In some embodiments, the second drive assembly may include a second motor 42 and a second coupling 50, the second motor 42 is connected to the second transmission shaft 44 through the second coupling 50, and the second motor 42 drives the second transmission shaft 44 to rotate through the second coupling 50. In some embodiments, the second transmission assembly may further include a second guide rail 48 arranged along the y-axis direction, used to support the second transmission member 46 and guide the second transmission member 46 to move, so that the second transmission member 46 can stably move along the second transmission shaft 44, and prevent the second transmission member 46 from tilting or tipping over. The second guide rail 48 may be arranged parallel to the second transmission shaft 44 and is a linear guide rail.

[0065] For example, reference may be made to Figure 1 , first guide rails 47 are provided on both sides of the first transmission shaft 43, the first guide rails 47 support the first transmission member 45, and the first motor 41 is connected to the first transmission shaft 43 through a first coupling 49. Second guide rails 48 are provided on both sides of the second transmission shaft 44, the second guide rails 48 support the second transmission member 46, and the second motor 42 is connected to the second transmission shaft 44 through a second coupling 50. The first motor 41 is connected to the control device 6 through a cable 61, and the second motor 42 is connected to the control device 6 through a cable 61. In some embodiments, the first transmission shaft 43 can be a ball screw, and the first transmission member 45 can be a nut. The second transmission shaft 44 can be a ball screw, and the second transmission member 46 can be a nut. The first motor 41 can be a stepper motor, and the second motor 42 can be a stepper motor.

[0066] The first transmission rod 51 is retractable, so that when the second transmission assembly drives the fixed frame 1 to move along the y-axis, the first transmission rod 51 does not affect the movement of the fixed frame 1. The second transmission rod 52 is retractable, so that when the first transmission assembly drives the fixed frame 1 to move along the x-axis, the second transmission rod 52 does not affect the movement of the fixed frame 1. The first transmission rod 51 can be a telescopic transmission rod, so that it can be retracted. The second transmission rod 52 can be a telescopic transmission rod, so that it can be retracted.

[0067] The sample pool control system of this embodiment can drive the sample pool 2 to move in the xy plane, and more accurately control the position of the sample pool 2. The sample pool control system of this embodiment can be applied to an imaging system, and the imaging system includes an imaging device 5 for acquiring an image of the sample in the sample pool 2. In some embodiments, the imaging device 5 can be arranged directly above the sample pool 2. For example, the sample pool control system can be applied to a fluorescence microscope, and the imaging device 5 can use a high-resolution camera, which can acquire a fluorescence image in the sample pool 2 in real time at a speed of at least 50 frames per second.

[0068] This embodiment also provides a sample imaging method, wherein the sample pool 2 is placed on a fixed frame 1, a first transmission assembly and a second transmission assembly are respectively connected to the fixed frame 1, the first transmission assembly is used to drive the fixed frame 1 to move along the x-axis, and the second transmission assembly is used to drive the fixed frame 1 to move along the y-axis. Figure 3 , Figure 3 A flow chart of a sample imaging method provided by an embodiment is shown in the figure. The sample imaging method comprises the following steps:

[0069] S11: moving the sample pool 2 to an initial position through the first transmission assembly and the second transmission assembly, and controlling the imaging device 5 to acquire an image of the sample in the sample pool 2 to obtain an image.

[0070] S12: Detecting a light spot in the image, and determining a target area of ​​the image according to features of the light spot.

[0071] S13: A moving path is planned according to the initial position and the position of the target area of ​​the image, and according to the moving path, the sample pool 2 is moved to the target position through the first transmission component and the second transmission component, so that the imaging device 5 acquires an image of the sample in the sample pool 2 when the sample pool 2 moves to the target position.

[0072] The first transmission assembly drives the fixed frame 1 to move along the x-axis, and the second transmission assembly drives the fixed frame 1 to move along the y-axis. Therefore, the first transmission assembly and the second transmission assembly can control the movement of the sample pool 2 and control the movement of the sample pool 2 in the xy plane.

[0073] The imaging device 5 is used for microscopic imaging of the sample. The sample generates light, so that there are light spots in the image obtained from the sample. The target area is determined according to the light spot characteristics in the image, so as to obtain an image of the position of the sample in the sample pool 2 corresponding to the target area.

[0074] The sample imaging method of this embodiment acquires an image of the sample in the sample pool when the sample pool is in the initial position, determines the target area according to the light spot characteristics of the image, further plans the moving path according to the initial position and the position of the target area of ​​the image, and further moves the sample pool to the target position through the first transmission component and the second transmission component to acquire an image of the sample in the sample pool. The sample imaging method of this embodiment can automatically control the movement of the sample pool to achieve imaging of the sample.

[0075] For example, reference may be made to Figure 4 , Figure 4 A specific flow chart of a sample imaging method provided in an embodiment. Initializing the position of the sample pool 2 means moving the sample pool 2 to an initial position, and the initial position provides a reference for the subsequent movement and positioning of the sample pool 2. In some embodiments, when the sample pool 2 is in the initial position, the center of the sample pool 2 is aligned with the optical lens of the imaging device 5. When the sample pool 2 is in the initial position, specifically, the center of the sample pool 2 can be aligned with the optical axis of the optical lens of the imaging device 5. The coordinates of the initial position in the xy coordinate system established in the moving plane of the sample pool 2 can be (0, 0).

[0076] In some embodiments, detecting a light spot in the image and determining a target area of ​​the image according to the light spot characteristics may include the following steps:

[0077] S21: performing a multi-layer convolution operation on the image to extract features at different levels from the image;

[0078] S22: generating a plurality of candidate detection frames in the image according to the features, and obtaining positions, categories, and confidences of the candidate detection frames;

[0079] S23: Filter out a target detection frame according to the confidence level of the candidate detection frame, so as to determine the target area according to the target detection frame.

[0080] Different levels of features are extracted from the image, including low-level features and high-level features. Low-level features include but are not limited to edge features or texture features, and high-level features include but are not limited to target shape or target position. Different levels of features can be extracted from the image through a convolutional neural network. Low-level features are captured through the first few layers of convolution, and high-level features are obtained through the latter few layers of convolution processing. A detection frame is generated for the target in the image through the anchor frame mechanism of the convolutional neural network. The target to be detected in the image is a light spot, and the candidate detection frame is used to frame the light spot. In some embodiments, the categories may include target particles and impurity particles. The target particles can emit light, and some impurities or other nanoparticles can also emit light. The target particles and impurity particles can be classified according to the shape, size or intensity of the light spot.

[0081] In some embodiments, filtering out the target detection frame according to the confidence of the candidate detection frame includes: filtering out the candidate detection frame whose confidence is within a preset range as the target detection frame. According to the calculated confidence score, the candidate detection frame with higher confidence can be filtered out as the target detection frame to improve the detection accuracy and stability. In some embodiments, the confidence of the detection frame is the probability that the detection frame contains the target multiplied by the intersection and union ratio of the detection frame and the real frame. The intersection and union ratio of the detection frame and the real frame represents the degree of overlap between the detection frame and the real frame. The calculation formula of confidence (Confidence) can be: Confidence = Pr(Object)×IoU, where Pr(Object) represents the probability that the detection frame contains the target, and IoU represents the intersection and union ratio of the detection frame and the real frame. For example, a certain predicted frame has a 70% probability of containing the target, that is, Pr(Object)=0.7, and its intersection and union ratio with the real frame is 0.6, then the confidence of the predicted frame is 0.7×0.6 = 0.42.

[0082] For example, reference may be made to Figure 5 , Figure 5 A flow chart of a method for detecting a target in an image of a sample imaging method provided in an embodiment. In some embodiments, the image can be preprocessed before performing multi-layer convolution operations on the image. The preprocessing may include normalizing the image and / or adjusting the image size to adapt to the image format required for the multi-layer convolution operation to ensure the quality and consistency of the image processing process. In some embodiments, the YOLOv5 target detection algorithm can be used to analyze the image, extract features from the image, generate a detection frame, and identify the dynamic behavior of the target. The method of this embodiment can efficiently and accurately detect the light spot in the image and determine the target area based on the light spot characteristics, which helps to improve the efficiency and accuracy of sample imaging.

[0083] In some embodiments, detecting a light spot in the image and determining a target area of ​​the image according to the light spot characteristics may include the following steps:

[0084] S31: extracting features from the image, and generating a plurality of target detection frames in the image according to the features, wherein the target detection frames are used to frame the light spots, and the area framed by the target detection frames in the image is the detection area;

[0085] S32: extracting features from the detection area layer by layer from the shallow layer to the deep layer, combining the features of each layer obtained to obtain a feature vector, and the feature vector includes the light spot information;

[0086] S33: Filter out the detection area whose light spot information meets the requirements as the target area.

[0087] Extracting features from the detection area from the shallow layer includes extracting basic features of the image, including but not limited to edge features or texture features, and extracting features from the detection area from the deep layer includes extracting higher-dimensional semantic information of the image, including but not limited to morphological features. The image can be processed by a shallow convolution layer to extract basic features of the image, and the image can be processed by a deep convolution layer to extract higher-dimensional semantic information. Extracting features from the detection area layer by layer can avoid the gradient vanishing problem and enable more stable acquisition of important information in the image. In some embodiments, the detection area can be processed by a residual block to extract deep-level features layer by layer, and the residual block can avoid the gradient vanishing problem through a "skip connection" method.

[0088] The imaging quality of the detection area is evaluated according to the feature vector or the light spot information to select the detection area with better imaging quality. For example, the light spot information may include but is not limited to the light spot intensity, the light spot distribution uniformity or density. The detection area with higher light spot intensity and better light spot distribution uniformity can be selected as the target area to ensure the observation effect of the selected area.

[0089] For example, reference may be made to Figure 6 , Figure 6 A flow chart of a method for extracting features from a detection area and screening a target area in a sample imaging method provided in an embodiment. In some embodiments, before extracting features from the detection area layer by layer from shallow to deep layers, the detection area is standardized to ensure that the detection area meets the requirements of the feature extraction network, thereby providing high-quality image data for subsequent feature extraction.

[0090] Extracting features from the image and generating multiple target detection frames in the image based on the features can be performed by the method described in the above steps S21 to S23. In some embodiments, the ResNet50 feature extraction algorithm can be used to extract features from the detection area layer by layer to obtain feature vectors to filter the target area. The ResNet50 feature extraction algorithm extracts features layer by layer through the residual block (ResidualBlocks) structure. The method of this embodiment can efficiently and accurately extract features from the detection area and filter the target area, which helps to improve the efficiency and accuracy of sample imaging.

[0091] In some embodiments, determining the target area of ​​the image according to the light spot characteristics may include the following steps:

[0092] S41: extracting features from the image, and generating a plurality of target detection frames in the image according to the features, wherein the target detection frames are used to frame the light spots, and the area framed by the target detection frames in the image is the detection area;

[0093] S42: Obtaining the light spot intensity of the detection area, and dividing the detection area into a plurality of blocks, obtaining the light spot intensity of any one of the plurality of blocks, and obtaining the light spot distribution uniformity of the detection area according to the light spot intensity of the plurality of blocks;

[0094] S43: According to the light spot intensity and / or the light spot distribution uniformity of each of the detection areas, the detection areas whose light spot intensity and / or the light spot distribution uniformity meet the requirements are screened out as the target areas.

[0095] In some embodiments, obtaining the spot intensity of the detection area may include: obtaining an average pixel value of the detection area to obtain the spot intensity of the detection area. The average pixel value of the detection area is used to represent the spot intensity of the detection area. Obtaining the spot intensity of the current block may include: obtaining an average pixel value of the current block to obtain the spot intensity of the current block. The average pixel value of the block is used to represent the spot intensity of the block.

[0096] In some embodiments, obtaining the uniformity of the spot distribution of the detection area according to the spot intensities of the multiple blocks includes: obtaining the standard deviation of the spot intensities of the multiple blocks to obtain the uniformity of the spot distribution of the detection area. The uniformity of the spot distribution of the detection area is characterized by the standard deviation of the spot intensities of the multiple blocks. The smaller the standard deviation, the more uniform the spot distribution in the detection area. Exemplarily, a detection area is divided into a 4×4 grid, the average pixel value of each block is calculated, and then the difference in the average pixel values ​​between the blocks is compared to obtain the uniformity of the spot distribution.

[0097] The detection area that meets the requirements of the spot intensity and / or the spot distribution uniformity is selected as the target area, and the detection area with higher spot intensity and better spot distribution uniformity can be selected as the target area to ensure the subsequent observation effect of the selected area. For image feature extraction, multiple target detection frames can be generated in the image according to the features by the method described in the above steps S21 to S23. In the above step S32, for obtaining the feature vector of the detection area, the spot information contained in the feature vector can be the feature vector containing the spot intensity and / or the spot distribution uniformity, and the spot intensity and / or the spot distribution uniformity can be obtained by the method described in the above step S42.

[0098] In some implementations, planning a moving path according to the initial position and the position of the target area of ​​the image may include the following steps:

[0099] S51: determining the target position according to the position of the target area of ​​the image;

[0100] S52: sequentially update the closed list, the open list and the current node for multiple times. In any update, add the current node to the closed list, add the adjacent nodes of the current node to the open list, and find the node with the smallest total cost from the open list as the current node in the next update, until the current node is the target position, then stop updating. In the first update, the initial position is used as the current node. The total cost describes the sum of the distance traveled from the initial position to the corresponding position of the node and the distance required to travel from the corresponding position of the node to the target position.

[0101] S53: Obtain the moving path according to each node in the closed list.

[0102] In the first update, the initial position is used as the current node, the current node (initial position) is added to the closed list, and the adjacent nodes of the current node are added to the open list. Further, the node with the smallest total cost is found from the open list and used as the current node in the next update.

[0103] In any update after the first update, the node found from the open list in the previous update is used as the current node in this update, the current node is added to the closed list, and the adjacent nodes of the current node are added to the open list. In addition, the node with the smallest total cost is found from the open list and used as the current node in the next update. When the current node after an update is the target position, it means that the target position has been reached, then the update is stopped, and the moving path is obtained according to the nodes added in sequence in the closed list.

[0104] For example, reference may be made to Figure 7 , Figure 7 A flow chart of a method for planning a moving path of a sample imaging method provided in an embodiment. An initial position and a target position are determined to provide basic data for planning the moving path.

[0105] The open list is used to add the neighboring nodes of the current node. In any update, the open list is updated according to the current node. For nodes that are neighboring nodes of the current node but are not yet in the open list, they are added to the open list. In some embodiments, the distance and relative position between the node and the neighboring node are determined by the moving step length of the first transmission component to the sample pool 2 and the moving step length of the second transmission component to the sample pool 2.

[0106] In any update, after updating the open list according to the current node, the total cost of any node in the open list is calculated. In any update, find the node with the smallest total cost from the open list, use this node as the current node in the next update, and move it to the closed list. Selecting nodes based on the total cost ensures the rationality and efficiency of path selection and avoids the exploration of invalid paths. In each update, the node with the smallest total cost is selected and moved to the closed list to obtain the moving path, which can obtain the optimal path or the shortest path from the initial position to the target position.

[0107] When adding a node to the open list and calculating the total cost of the node. In some embodiments, the total cost of the node can be calculated using a total cost function, which can be expressed as: f(n) = g(n) + h(n), where g(n) represents the actual cost from the starting node to the node, representing the distance traveled from the starting node to the node, and h(n) represents the heuristic estimated cost from the node to the target node, representing the distance required to travel from the node to the target node.

[0108] After stopping updating, the path planning is completed, and the nodes in the closed list are traced back from the end point to the starting point to generate the optimal path composed of the minimum total cost nodes, and the nodes correspond to the sample pool positions. In some embodiments, when the current node is the target position or the open list is empty, the updating is stopped and the path planning is completed. In this embodiment, the A* algorithm is used to plan the moving path of the sample pool 2.

[0109] Further, according to the planned moving path, an instruction is generated and transmitted to the first transmission component and the second transmission component, so that the sample pool 2 is moved by the first transmission component and the second transmission component, so that the sample pool 2 is smoothly moved to the target position along the planned path on the xy plane. Figure 1 The sample pool control system shown can generate instructions or control signals by the control device 6 and transmit them to the first motor 41 and the second motor 42 respectively.

[0110] In some embodiments, according to the moving path, moving the sample pool 2 to the target position through the first transmission component and the second transmission component includes: when the sample pool 2 is moved to any position of the moving path, if the movement is blocked or the position of the sample pool 2 deviates from the moving path, the moving path is re-planned according to the target position and the current position of the sample pool 2, so that according to the re-planned moving path, the sample pool 2 is moved to the target position through the first transmission component and the second transmission component. In this embodiment, the path can be adjusted in real time during the movement of the sample pool 2.

[0111] In some embodiments, detecting a light spot in an image and determining a target area of ​​the image according to the light spot characteristics includes: determining multiple target areas of the image according to the light spot characteristics. Accordingly, for any target area, a moving path is planned according to the initial position and the position of the target area, so that according to the moving path, the sample pool 2 is moved to the target position corresponding to the target area through the first transmission component and the second transmission component, so that the imaging device 5 acquires an image of the sample in the sample pool 2 when the sample pool 2 moves to the target position. In this embodiment, multi-area and multi-position imaging of the sample is achieved.

[0112] In some embodiments, detecting a light spot in an image, and determining a target area of ​​the image based on the light spot characteristics includes: determining the first to Mth target areas of the image based on the light spot characteristics. Accordingly, planning a moving path based on the initial position and the position of the target area of ​​the image includes: sequentially planning the first to Mth sub-movement paths, wherein the first sub-movement path is planned based on the initial position and the position of the first target area, the first target area is the target area with the smallest distance from the corresponding position in the first to Mth target areas to the initial position, and the mth sub-movement path is planned based on the position of the m-1th target area and the position of the mth target area, the mth target area is the target area with the smallest distance from the position in the remaining target areas to the position of the m-1th target area, m∈[2,M], M is a positive integer greater than or equal to 2. Correspondingly, according to the moving path, moving the sample pool 2 to the target position through the first transmission component and the second transmission component includes: moving the sample pool 2 through the first transmission component and the second transmission component according to the first to M-th sub-moving paths in sequence, so that the sample pool 2 is moved to the first to M-th target positions in sequence, and the first to M-th target positions are the sample pool positions corresponding to the first to M-th target areas in sequence. When the sample pool 2 is moved to any target position, the imaging device 5 is used to acquire an image of the sample in the sample pool 2. The position of the target area refers to the position of the target area in the image, and the corresponding position of the target area refers to the sample pool position corresponding to the target area. In this embodiment, the moving path is planned in sequence according to the distance of each target area, which can improve the efficiency of imaging multiple areas of the sample. Exemplarily, eighty percent of the radius of the sample pool 2 can be used as its activity limit, and the moving accuracy of the sample pool 2 can be several hundred microns, and the multiple target areas detected are not repeated as much as possible.

[0113] In some embodiments, when the sample pool 2 moves to the target position and the imaging device 5 acquires an image of the sample in the sample pool 2, the moving path and imaging plan of the sample pool 2 can be adjusted based on the acquired image, thereby dynamically optimizing the imaging process and ensuring that the imaging task always maintains high efficiency and accuracy at different positions. Through real-time dynamic adjustment, the overall experimental efficiency and the reliability of the results are improved.

[0114] In some embodiments, when the sample pool 2 moves to the target position and the imaging device 5 acquires an image of the sample in the sample pool 2, the imaging parameters of the imaging device 5 can be adjusted according to the acquired image to ensure the clarity and signal stability of the acquired image. The imaging parameters include but are not limited to exposure time or gain.

[0115] For the sample pool control system described in any of the above embodiments, the imaging device 5 is connected to the control device 6, and the image of the sample in the sample pool 2 acquired by the imaging device 5 is transmitted to the control device 6, and the control device 6 performs the process described in the sample imaging method described in any of the above embodiments. The image of the sample in the sample pool 2 acquired by the imaging device 5 is transmitted to the control device 6, and the control device 6 can store the image. The characteristic data, position data, and path data generated by the control device 6 in executing the sample imaging method described in any of the above embodiments can be stored.

[0116] The imaging device 5 is connected to the control device 6 via a cable 61, and the control device 6 is respectively connected to the first motor 41 and the second motor 42 via cables 61. The control device 6 can generate instructions or control signals and transmit them to the first motor 41 and the second motor 42 respectively to control the moving sample pool 2.

[0117] In some embodiments, the imaging system can perform self-checks. During the experiment, self-checks can be performed regularly. The self-checks include: checking whether the power supply lines are connected normally, whether the first transmission assembly and the second transmission assembly can control the movement of the sample pool 2, and whether the imaging device 5 can capture images normally; whether the image acquired by the imaging device 5 is normal. If there are no fluorescent spots in the image or the fluorescent spots are too dense or too sparse, or if there are impurity fluorescent spots, it can be considered that the image acquisition has failed. If a fluorescent signal image that meets the requirements is collected, it is considered normal. This can be judged manually, and the specific requirements for the images required for each acquisition are different. If the system detects an abnormal situation after self-checking, it can be dynamically reset, automatically perform the reset operation and send a warning signal to inform the operator to ensure the continuous stability of the experiment.

[0118] The sample pool control system and sample imaging method of the present embodiment can realize the multi-position imaging system of fluorescence microscope of intelligent mobile sample pool, which can more accurately identify the fluorescence signal area in the sample, and automatically adjust the position of the sample pool, optimize the imaging effect, and improve the experimental efficiency and imaging accuracy. The system uses computer control and deep learning algorithms, including YOLOv5 target detection, ResNet50 feature extraction and A* path planning, etc., to achieve accurate positioning and multi-region imaging of the sample pool on the xy plane. The sample fluorescence image is acquired in real time by the high-resolution camera integrated by the system, and the optimal imaging area is automatically identified and multi-position imaging tasks are generated in combination with the deep learning algorithm, so that the sample pool can be accurately and stably moved to the target position during the experiment. According to the optimal path automatically generated, the sample pool automatically and smoothly completes the multi-position movement and imaging tasks, ensuring the high precision of the sample pool position and the high quality of image acquisition, effectively improving the automation and intelligence level of the experiment, and is particularly suitable for the multi-region fluorescence imaging needs in the fields of life sciences and materials sciences.

[0119] The sample pool control system and sample imaging method of this embodiment can realize a fluorescence microscope system that combines intelligent control and multi-position imaging functions. The system drives the sample pool to move precisely in the xy plane through the sample pool control system, and realizes multi-position automated imaging by combining target recognition and path planning. The system not only improves experimental efficiency but also reduces errors in manual operation through real-time image processing and intelligent algorithm decision-making. It is suitable for efficient, multi-position fluorescence imaging, and is particularly suitable for large-scale imaging tasks under complex experimental conditions.

[0120] The sample pool control system and sample imaging method provided by the present invention are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. It should be pointed out that for ordinary technicians in this technical field, without departing from the principle of the present invention, several improvements and modifications can be made to the present invention, and these improvements and modifications also fall within the scope of protection of the claims of the present invention.

Claims

1. A sample pool control system, characterized in that: include: A fixed frame for placing the sample pool; A first transmission assembly comprises a first transmission shaft, a first transmission member and a first transmission rod, wherein the first transmission shaft is arranged along the x-axis direction, the first transmission member is connected to the first transmission shaft, one end of the first transmission rod is connected to the first transmission member, and the other end is connected to the fixed frame, and the first transmission shaft is used to drive the first transmission member to move along the first transmission shaft, so that the first transmission member drives the fixed frame to move along the x-axis through the first transmission rod; A second transmission assembly includes a second transmission shaft, a second transmission member and a second transmission rod, wherein the second transmission shaft is arranged along the y-axis direction, the second transmission member is connected to the second transmission shaft, one end of the second transmission rod is connected to the second transmission member, and the other end is connected to the fixed frame, and the second transmission shaft is used to drive the second transmission member to move along the second transmission shaft, so that the second transmission member drives the fixed frame to move along the y-axis through the second transmission rod; A control device is connected to the first transmission assembly and the second transmission assembly, respectively, and is used to transmit control signals to the first transmission assembly and the second transmission assembly, respectively, so as to control the first transmission shaft to drive the first transmission member to move and / or control the second transmission shaft to drive the second transmission member to move.

2. The sample pool control system according to claim 1, characterized in that: The fixing frame is provided with a fixing ring, the sample pool is placed in the fixing ring, the fixing ring is provided with a rotating part, the first end and the second end of the fixing ring are respectively connected to the periphery of the rotating part, so that the rotating part rotates to change the diameter of the fixing ring.

3. The sample pool control system according to claim 1, characterized in that: The first transmission assembly further includes a first driving assembly connected to the first transmission shaft, and configured to drive the first transmission shaft to rotate, so that the first transmission shaft drives the first transmission member to move along the first transmission shaft; The second transmission assembly also includes a second drive assembly connected to the second transmission shaft, which is used to drive the second transmission shaft to rotate, so that the second transmission shaft drives the second transmission member to move along the second transmission shaft.

4. The sample pool control system according to claim 1, characterized in that: The first transmission assembly further includes a first guide rail arranged along the x-axis direction, for supporting the first transmission member and guiding the first transmission member to move; The second transmission assembly also includes a second guide rail arranged along the y-axis direction, which is used to support the second transmission member and guide the second transmission member to move.

5. A sample imaging method, characterized in that: The sample pool is placed on a fixed frame, and a first transmission assembly and a second transmission assembly are respectively connected to the fixed frame, the first transmission assembly is used to drive the fixed frame to move along the x-axis, and the second transmission assembly is used to drive the fixed frame to move along the y-axis; The sample imaging method comprises: The sample pool is moved to an initial position by the first transmission assembly and the second transmission assembly, and an imaging device is controlled to acquire an image of the sample in the sample pool to obtain an image; Detecting a light spot in the image, and determining a target area of ​​the image according to the light spot characteristics; A moving path is planned according to the initial position and the position of the target area of ​​the image, so that the sample pool is moved to the target position through the first transmission component and the second transmission component according to the moving path, so that the imaging device acquires an image of the sample in the sample pool when the sample pool moves to the target position.

6. The sample imaging method according to claim 5, characterized in that: Detecting a light spot in the image and determining a target area of ​​the image according to the light spot characteristics includes: Performing a multi-layer convolution operation on the image to extract features at different levels from the image; Generating a plurality of candidate detection frames in the image according to the features, and obtaining positions, categories, and confidences of the candidate detection frames; The target detection frame is screened out according to the confidence level of the candidate detection frame, so as to determine the target area according to the target detection frame.

7. The sample imaging method according to claim 5, characterized in that: Detecting a light spot in the image and determining a target area of ​​the image according to the light spot characteristics includes: Extracting features from the image, generating a plurality of target detection frames in the image according to the features, wherein the target detection frames are used to frame the light spots, and the area framed by the target detection frames in the image is the detection area; Extracting features from the shallow layer to the deep layer of the detection area layer by layer, combining the features of each layer to obtain a feature vector, wherein the feature vector includes light spot information; The detection area whose spot information meets the requirements is screened out as the target area.

8. The sample imaging method according to claim 5, characterized in that: Determining the target area of ​​the image according to the light spot characteristics includes: Extracting features from the image, generating a plurality of target detection frames in the image according to the features, wherein the target detection frames are used to frame the light spots, and the area framed by the target detection frames in the image is the detection area; Obtaining the light spot intensity of the detection area, dividing the detection area into a plurality of blocks, obtaining the light spot intensity of any one of the plurality of blocks, and obtaining the light spot distribution uniformity of the detection area according to the light spot intensity of the plurality of blocks; According to the light spot intensity and / or the light spot distribution uniformity of each of the detection areas, the detection areas whose light spot intensity and / or the light spot distribution uniformity meet the requirements are screened out as the target areas.

9. The sample imaging method according to claim 5, characterized in that: Planning a moving path according to the initial position and the position of the target area of ​​the image includes: Determining the target position according to the position of the target area of ​​the image; Update the closed list, the open list and the current node in sequence for multiple times. In any update, add the current node to the closed list, add the adjacent nodes of the current node to the open list, and find the node with the smallest total cost from the open list as the current node in the next update, until the current node is the target position, then stop updating. In the first update, the initial position is used as the current node. The total cost describes the sum of the distance traveled from the initial position to the corresponding position of the node and the distance required to travel from the corresponding position of the node to the target position. The moving path is obtained according to each node in the closed list.

10. The sample imaging method according to claim 5, characterized in that: Detecting a light spot in the image, and determining a target area of ​​the image according to the light spot characteristics comprises: determining first to Mth target areas of the image according to the light spot characteristics, where M is a positive integer greater than or equal to 2; Planning a moving path according to the initial position and the position of the target area of ​​the image includes: The first to M-th sub-movement paths are planned sequentially, wherein the first sub-movement path is planned according to the initial position and the position of the first target area, the first target area is the target area with the smallest distance from the corresponding position in the first to M-th target areas to the initial position, and the m-th sub-movement path is planned according to the position of the m-1-th target area and the position of the m-th target area, the m-th target area is the target area with the smallest distance from the position in the remaining target areas to the position of the m-1-th target area, m∈[2,M]; According to the moving path, moving the sample pool to a target position by the first transmission assembly and the second transmission assembly includes: According to the first to Mth sub-movement paths, the sample pool is moved by the first transmission component and the second transmission component in sequence, so that the sample pool is moved to the first to Mth target positions in sequence, and the first to Mth target positions are the sample pool positions corresponding to the first to Mth target areas in sequence.

Images