Image analysis system and method for identifying duplicate cells

Abstract

The present invention provides an image analysis system and a method for identifying duplicate cells. The system includes an imaging device and an image analysis device. The camera unit in the imaging device photographs the sample to be tested on the smear to obtain a first image and obtains the first image information of the first image; and photographs the target cells in the sample to be tested to obtain multiple images, and obtains the second image information of the second image and the third image information of the third image in the multiple images; the image analysis device is used to analyze the second and third image information with the first image information respectively, determine the first and second corresponding positions of the second and third images on the first image, and determine that the target cells in the second image and the third image are duplicated target cells when the distance between the first and second corresponding positions is less than or equal to a preset distance threshold. The present invention identifies duplicate cells by determining the corresponding positions of the images, which can be achieved by using the existing system, and the amount of calculation in the identification process is small.

Description

Technical Field

[0001] The present invention relates to the field of image analysis systems, and more particularly, to an image analysis system and a method for identifying duplicate cells. Background Art

[0002] The current image analysis system (e.g., a blood cell digital image analysis system) performs cell analysis in the following manner: use a low-power objective lens (e.g., 10x) to capture images of cells to be tested in order to locate cells (e.g., white blood cells), and then use a high-power objective lens (e.g., 100x) to capture images of each cell to be tested located by the low-power objective lens. However, due to mechanical problems such as motor step loss or different thread pitches, when using a high-power objective lens to locate a single cell, there is an inherent problem of inaccurate positioning, resulting in repeated shooting, i.e., the same white blood cells are contained in the images captured twice by the high-power objective lens, which makes it difficult for users to observe the morphology of white blood cells and thus determine the disease.

[0003] Therefore, there is a need in the art for an image analysis system and a method for identifying duplicate cells to solve the above problems. Summary of the invention

[0004] The present invention is proposed to solve the above problems. According to one aspect of the present invention, an image analysis system is provided, which includes an imaging device and an image analysis device, wherein: the imaging device includes a camera unit, the camera unit photographs the sample to be tested on the smear to obtain a first image, and obtains first image information of the first image; the camera unit photographs the target cells in the sample to be tested on the smear to obtain multiple images, and obtains image information of each of the multiple images, wherein the multiple images include a second image and a third image, and the image information includes second image information of the second image and third image information of the third image; the image analysis device is used to: analyze the second image information and the third image information respectively with the first image information, determine the first corresponding position of the second image on the first image and the second corresponding position of the third image on the first image; when the distance between the first corresponding position and the second corresponding position is less than or equal to a preset distance threshold, determine that the target cells in the second image and the third image are target cells that are repeatedly photographed.

[0005] According to another aspect of the present invention, there is provided an image analysis system, the image analysis system comprising an imaging device and an image analysis device, wherein: the imaging device comprises a camera unit, the camera unit photographs target cells contained in a sample to be tested on a smear to obtain a first image and a second image, and obtains first image information of the first image and second image information of the second image; the image analysis device is used to: obtain the position coordinates of a first target cell in the first image on the first image; analyze the first image information and the second image information to determine the corresponding position of the second image on the first image; based on the corresponding position, determine the corresponding coordinates of a second target cell in the second image on the first image; when the distance between the position coordinates and the corresponding coordinates is less than or equal to a preset distance threshold, determine that the first target cell and the second target cell are target cells that are photographed repeatedly.

[0006] According to another aspect of the present invention, there is provided an image analysis system, which includes an imaging device and an image analysis device, wherein: the imaging device includes a camera unit, which photographs target cells contained in a sample to be tested on a smear to obtain a first image and a second image, and obtains first image information of the first image and second image information of the second image; the image analysis device is used to: analyze the first image information and the second image information to determine a corresponding position of the second image on the first image; when the degree of overlap between the corresponding position and the position of the first image is greater than or equal to a preset overlap threshold, determine that the first image and the second image are repeatedly shot images, so that the target cells on the first image and the second image are target cells that are repeatedly shot with each other.

[0007] According to yet another aspect of the present invention, there is provided a sample analysis system, comprising a blood analysis device, a smear preparation device, an image analysis device and a control device, wherein the image analysis device comprises the image analysis system as described above.

[0008] According to yet another aspect of the present invention, a method for identifying duplicate cells in an image analysis system is provided, the method comprising: photographing a sample to be tested on a smear to obtain a first image, and acquiring first image information of the first image; photographing target cells in the sample to be tested on the smear to obtain multiple images, and acquiring image information of each of the multiple images, wherein the multiple images include a second image and a third image, and the image information includes second image information of the second image and third image information of the third image; analyzing the second image information and the third image information respectively with the first image information to determine a first corresponding position of the second image on the first image and a second corresponding position of the third image on the first image; and determining that the target cells in the second image and the third image are duplicated target cells when the distance between the first corresponding position and the second corresponding position is less than or equal to a preset distance threshold.

[0009] According to yet another aspect of the present invention, there is provided a method for identifying duplicate cells by an image analysis system, the method comprising: photographing target cells contained in a sample to be tested on a smear to obtain a first image and a second image, acquiring first image information of the first image and second image information of the second image, and acquiring position coordinates of a first target cell in the first image on the first image; analyzing the first image information and the second image information to determine a corresponding position of the second image on the first image; based on the corresponding position, determining corresponding coordinates of a second target cell in the second image on the first image, and when a distance between the position coordinates and the corresponding coordinates is less than or equal to a preset distance threshold, determining that the first target cell and the second target cell are target cells photographed repeatedly with each other.

[0010] According to yet another aspect of the present invention, there is provided a method for identifying duplicate cells by an image analysis system, the method comprising: photographing target cells contained in a sample to be tested on a smear to obtain a first image and a second image, acquiring first image information of the first image and second image information of the second image; analyzing the first image information and the second image information to determine a corresponding position of the second image on the first image; and determining that the first image and the second image are duplicate images when a degree of overlap between the corresponding position and the position of the first image is greater than or equal to a degree of overlap threshold, so that the target cells on the first image and the second image are duplicate target cells of each other.

[0011] According to another aspect of the present invention, there is provided a computer-readable storage medium comprising computer-executable instructions, wherein when the computer-executable instructions are executed by a processor, the method for identifying duplicate cells in an image analysis system as described above can be executed.

[0012] According to the image analysis system and the method for identifying duplicate cells in the image analysis system according to the embodiments of the present invention, duplicate cells are identified by determining the corresponding position of one image on another image. This can be achieved using the existing system without the need for additional devices, and the amount of computation required in the identification process is small. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The above and other purposes, features and advantages of the present invention will become more apparent by describing the embodiments of the present invention in more detail in conjunction with the accompanying drawings. The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0014] Figure 1 A schematic structural block diagram of an image analysis system according to an embodiment of the present invention is shown;

[0015] Figure 2 shows an exemplary first image according to one embodiment of the present invention;

[0016] Figure 3 shows an exemplary second image according to one embodiment of the present invention;

[0017] Figure 4 A schematic diagram showing analysis of a first image and a second image using a sliding window method according to an embodiment of the present invention is shown;

[0018] Figure 5 An exemplary integral image according to an embodiment of the present invention is shown, wherein the coordinates of four vertices of the sliding window are shown;

[0019] Figure 6 A schematic diagram showing analysis of a first image and a second image when a sliding window is partially located outside the first image according to an embodiment of the present invention;

[0020] Figure 7 A schematic diagram of the structure of a sample analysis system according to an embodiment of the present invention is shown;

[0021] Figure 8 A flowchart showing the steps of a method for identifying duplicate cells in an image analysis system according to an embodiment of the present invention is shown;

[0022] Fig. 9 A flowchart showing a method for identifying duplicate cells in an image analysis system according to another embodiment of the present invention is shown;

[0023] Fig.10 A flowchart showing the steps of a method for identifying duplicate cells in an image analysis system according to another embodiment of the present invention is shown. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical scheme and advantages of the present invention more obvious, the exemplary embodiments according to the present invention will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments of the present invention, and it should be understood that the present invention is not limited to the exemplary embodiments described herein. Based on the embodiments of the present invention described in the present invention, all other embodiments obtained by those skilled in the art without creative work should fall within the protection scope of the present invention.

[0025] In order to solve the above problems, an embodiment of the present invention provides an image analysis system and a method for identifying duplicate cells for an image analysis system, wherein the image analysis system includes an imaging device and an image analysis device, wherein: the imaging device includes a camera unit, the camera unit photographs a sample to be tested on a smear to obtain a first image, and obtains first image information of the first image; the camera unit photographs target cells in the sample to be tested on the smear to obtain multiple images, and obtains image information of each of the multiple images, wherein the multiple images include a second image and a third image, and the image information includes second image information of the second image and third image information of the third image; the image analysis device is used to: analyze the second image information and the third image information respectively with the first image information, determine a first corresponding position of the second image on the first image and a second corresponding position of the third image on the first image; and determine that the target cells in the second image and the third image are duplicated target cells when the distance between the first corresponding position and the second corresponding position is less than or equal to a preset distance threshold.

[0026] The image analysis system and the method for identifying duplicate cells in the image analysis system of the embodiment of the present invention identify duplicate cells by determining the corresponding position of one image on another image. This can be achieved using the existing system without the need for additional devices, and the computational complexity of the identification process is small.

[0027] The solution of the present invention is described in detail below in conjunction with specific embodiments.

[0028] Embodiment 1

[0029] This embodiment provides an image analysis system. Figure 1 , Figure 1 FIG. 1 shows a schematic structural block diagram of an image analysis system 10 according to an embodiment of the present invention. Figure 1 As shown, the image analysis system 10 may include an imaging device 100 and an image analysis device 200. The imaging device 100 is used to photograph the target cells in the sample to be tested smeared on the smear to obtain an image; the image analysis device 200 is used to analyze the image of the target cells. Exemplarily, the sample to be tested may be a blood sample, etc. Exemplarily, the target cells may be white blood cells, neutrophils, red blood cells, etc., which is not limited in the present invention.

[0030] Wherein, the imaging device 100 may include an objective lens unit 110 and a camera unit 120. Wherein, the objective lens unit 110 may include a first objective lens and a second objective lens. Exemplarily, the first objective lens may be a low-power objective lens, such as a 10-fold objective lens, etc., and the second objective lens may be a high-power objective lens, such as a 100-fold objective lens, etc. Exemplarily, the first objective lens and the second objective lens may also be objective lenses of the same magnification, such as both 100-fold objective lenses. The objective lens unit 110 may also include a third objective lens, etc., and the third objective lens may be, for example, a 40-fold objective lens, etc. It should be understood that the above-mentioned low-power objective lens and high-power objective lens are relative, and do not specifically refer to certain magnification objective lenses as low-power objective lenses, or certain magnification objective lenses as high-power objective lenses. Wherein, the camera unit 120 may include any camera, camera head, etc. known in the art, such as a CCD camera, a CMOS camera, etc., and the present invention is not limited to this.

[0031] The camera unit 120 photographs the sample to be tested on the smear to obtain a first image, and obtains first image information of the first image. Exemplarily, the first image can be obtained by photographing using a first objective lens. Exemplarily, the first objective lens can be a low-power objective lens, such as a 10-power objective lens, etc. At this time, the field of view of the first objective lens can be all samples to be tested, and the corresponding first image can include all target cells. Exemplarily, the first image information may include pixel information, feature information, and other information of the first image.

[0032] The imaging unit 120 also photographs the target cells in the sample to be tested on the smear to obtain multiple images, and obtains the image information of each of the multiple images. Exemplarily, the multiple images can be obtained by photographing using a second objective lens. Exemplarily, the second objective lens can be a high-power objective lens, such as a 100-fold objective lens, etc. At this time, the second objective lens can be used to photograph each target cell in the sample to be tested one by one, thereby obtaining multiple images. Exemplarily, the image information of each image may include information such as pixel information, feature information, etc. of each image.

[0033] The multiple images may include a second image, a third image, a fourth image, .... Accordingly, the image information may include second image information, third image information, fourth image information, .... The second, third, fourth, ... are only used to distinguish different images and corresponding image information in the multiple images, and do not specifically refer to a certain image or a certain image information.

[0034] Since the first image is taken with a low-power objective lens, its field of view is all the samples to be tested on the entire smear, so all target cells can be included in the first image, such as Figure 2 As shown; when each of the multiple images is taken with a high-power objective lens, its field of view is a small area on the smear where a target cell is located. Therefore, the second image, the third image, etc. can include a cell to be tested. When two or three cells are close to each other, they can also include two or three cells, such as Figure 3 shown.

[0035] The image analysis device 200 can be used to analyze the image information of each of the multiple images and the first image information, determine the corresponding position of each image on the first image, and determine whether there are target cells that are repeatedly photographed in each of the multiple images based on the corresponding position. The corresponding position of each image on the first image is the area on the first image to which each image corresponds.

[0036] Exemplarily, the image analysis device 200 can analyze the second image information, the third image information and the first image information respectively, determine the first corresponding position of the second image on the first image and the second corresponding position of the third image on the first image, and when the distance between the first corresponding position and the second corresponding position is less than or equal to a preset distance threshold, it is determined that the target cells in the second image and the third image are target cells that are repeatedly photographed. That is, if the distance between the first area on the first image corresponding to the second image and the second area on the first image corresponding to the third image is less than or equal to the preset distance threshold, it is determined that the second image and the third image are images that are repeatedly photographed, so that the target cells in the second image and the third image are target cells that are repeatedly photographed.

[0037] Exemplarily, the preset distance threshold may be set to be approximately equal to the size of the target cell, such as about 5 μm, which is not limited in the present invention.

[0038] Exemplarily, the image analysis device 200 may use an image registration algorithm to analyze the second image information, the third image information and the first image information respectively, and determine the first corresponding position of the second image on the first image and the second corresponding position of the third image on the first image. It should be understood that other methods may also be used to determine the first corresponding position of the second image on the first image and the second corresponding position of the third image on the first image, and the present invention is not limited thereto.

[0039] Since the image analysis device 200 uses an image registration algorithm to analyze two images, the process of determining the corresponding position of one image on the other image is similar. Therefore, the following is explained by taking the image analysis device 200 using an image registration algorithm to analyze the second image information and the first image information to determine the first corresponding position of the second image on the first image as an example.

[0040] Exemplarily, when the image registration algorithm is used to analyze the second image information and the first image information, the image analysis device 200 can extract pixel information or feature information from the first image information and the second image information, and determine the first corresponding position of the second image on the first image based on the pixel information or feature information. Exemplarily, the algorithm for determining the corresponding position of the image based on the pixel information may include the mean absolute difference algorithm (MAD), the absolute error sum algorithm (SAD), the error square sum algorithm (SSD), the mean error square sum algorithm (MSD), the normalized product correlation algorithm (NCC), the sequential similarity detection algorithm (SSDA), the hadamard transform algorithm (SATD), the local gray value coding algorithm, etc. Specifically, the method for determining the corresponding position of the image based on the feature information may include: first extracting the features of the image, then generating the feature descriptor, and finally matching the features of the two images according to the similarity of the descriptors. Among them, the features of the image can be mainly divided into features such as points, lines (edges), regions (surfaces), etc., and can also be divided into local features and global features. Exemplarily, methods for determining the corresponding positions of images based on point features may include Harris, Harr-like, HOG, LBP, SIFT and other algorithms, and methods for determining the corresponding positions of images based on edge features may include LoG operator, Robert operator, Sobel operator, Prewitt operator, Canny operator and the like.

[0041] Exemplarily, when determining the first corresponding position of the second image on the first image based on pixel information, the image analysis device 200 can use the pixel information of both the first image and the second image to establish a similarity measurement index, and determine the first corresponding position of the second image on the first image based on the similarity measurement index.

[0042] In order to improve the discrimination of the similarity measurement index, a similarity measurement index may be established based on the average pixel value of the second image and the first image. For example, the similarity measurement index γ may be established using the following formula:

[0043]

[0044] Among them, x and y are the coordinates of the pixel points respectively, and f(x, y) is the pixel value of each pixel point in a certain area on the first image. is the average pixel value of all pixels in the area on the first image, g(x,y) is the pixel value of each pixel on the second image, is the average pixel value of all pixels on the second image. It should be understood that f(x, y) can also be used. Represent the second image, using g(x,y), The formula of the present invention can improve the discrimination of the similarity measurement index and better distinguish the target cells in the second image in the first image.

[0045] Exemplarily, the image analysis device 200 may use a sliding window method to determine the value of the similarity measurement index, thereby determining the first corresponding position of the second image on the first image.

[0046] Specifically, Figure 4 As shown, the sliding window method may include: setting a sliding window so that the sliding window slides along a predetermined path on the first image, wherein the size of the sliding window is the same as the size of the second image; during the sliding process of the sliding window, calculating in real time the value of a similarity measurement index between the second image and the area of ​​the first image located within the sliding window; selecting the maximum value of the similarity measurement index, and the area of ​​the first image within the sliding window corresponding to the maximum value is the first corresponding position of the second image on the first image.

[0047] In one embodiment, the predetermined path may include a path from left to right and from top to bottom on the first image. In another embodiment, the predetermined path may include It should be understood that the predetermined path may also be other suitable paths, and the present invention is not limited thereto.

[0048] When the shooting field of the second image is at the edge of the shooting field of the first image, there will be an edge problem, which makes the value of the correlation metric low, so that the correct corresponding position cannot be found. Therefore, in one embodiment, if the sliding window is partially located outside the first image, the image analysis device 200 can also calculate the value of the similarity metric based on a preset overlap threshold.

[0049] Specifically, if the ratio of the area of ​​the overlapping portion of the sliding window and the first image to the total area of ​​the sliding window is greater than or equal to the overlapping threshold, it indicates that most of the sliding window is in the first image at this time. At this time, the image analysis device 200 can calculate the value of the similarity measurement index between the portion of the first image that overlaps with the sliding window and the corresponding portion of the second image. Figure 6 As shown, at this time, only the value of the similarity metric index between the dotted area in the sliding window on the first image and the dotted area on the second image is calculated. If the ratio of the area of ​​the overlapping part of the sliding window and the first image to the total area of ​​the sliding window is less than the overlap threshold, it means that only a small part of the sliding window is in the first image at this time. At this time, the overlapping area of ​​the field of view of the two images is very small, and the accuracy of the similarity metric index is low. Therefore, the image analysis device 200 can calculate the similarity metric index as zero. Among them, the overlap threshold can be set according to experience, for example, it can be set to 0.6-0.8, etc., and the present invention is not limited to this.

[0050] Before analyzing the first image and the second image using the sliding window method, the image analyzing device 200 needs to pre-process the first image and the second image.

[0051] Exemplarily, the preprocessing may include resampling the first image and / or the second image so that the resolution of the first image and the second image are the same, that is, the size represented by each pixel on the two images is the same. Resampling may include upsampling and downsampling. Exemplarily, the resolution of the first image may be kept unchanged, and the second image may be downsampled to the same resolution as the first image, or the resolution of the second image may be kept unchanged, and the first image may be upsampled to the same resolution as the second image, or the first image and the second image may be resampled to a certain resolution at the same time, and the present invention is not limited to this. The resampling method may adopt the nearest neighbor interpolation method, bilinear interpolation method, cubic convolution interpolation method, etc., which are well known in the art, and the present invention is not limited to this.

[0052] In order to reduce the amount of calculation, the preprocessing may also include converting both the first image and the second image into grayscale images before resampling the first image and / or the second image. The method of converting a color image into a grayscale image is well known and will not be described in detail here.

[0053] Since the value of the similarity metric index between the second image and the area of ​​the first image within the sliding window must be recalculated each time the sliding window slides one pixel, many positions need to be traversed, so the amount of calculation is very large. In order to optimize the operation speed, in one embodiment, the image analysis device 200 may first transfer the first image and the second image to the frequency domain, and then calculate the value of the similarity metric index between the second image and the area of ​​the first image within the sliding window. The method of transferring the first image and the second image to the frequency domain may be the FFT (Fast Fourier Transform) method, etc., which will not be described in detail here.

[0054] In order to optimize the operation speed, in another embodiment, the image analysis device 200 may use the integral graph method to calculate the value of the similarity measurement index between the second image and the area of ​​the first image located in the sliding window. First, the image analysis device 200 may first construct an array as an integral image, the width and height of the integral image being the same as those of the first image, and then assign values ​​to the array, with the value of each point being the sum of the pixel values ​​of all the pixels in the coverage area from the upper left corner of the first image to the point; then the integral image may be used to conveniently calculate the sum of the pixel values ​​of all the pixels in the sliding window, and then the value of the similarity measurement index between the second image and the area of ​​the first image located in the sliding window may be conveniently calculated. Figure 5 As shown in the figure, the sum of the pixel values ​​of all pixels in the sliding window is f(x2,y2)+f(x1,y1)-f(x1,y2)-f(x2,y1), where (x1,y1), (x2,y1), (x1,y2) and (x2,y2) are the coordinates of the four vertices of the sliding window respectively.

[0055] In one embodiment, the image analysis device 200 can obtain the first corresponding coordinates and the second corresponding coordinates of the first target cell on the second image and the second target cell on the third image on the first image, respectively, based on the first corresponding position of the second image on the first image and the second corresponding position of the third image on the first image. Specifically, the image analysis device 200 can obtain the coordinates of the first target cell on the second image, and combine the coordinates with the first corresponding position to obtain the first corresponding coordinates of the first target cell on the first image, and use a similar method to obtain the second corresponding coordinates of the second target cell on the first image. Then, the image analysis device 200 can determine that the first target cell and the second target cell are target cells that are repeatedly photographed when the distance between the first corresponding coordinates and the second corresponding coordinates is less than or equal to a preset distance threshold.

[0056] Exemplarily, as described above, the preset distance threshold can be set to be approximately equal to the size of the target cell, for example, about 5 μm. At this time, if the distance between the first corresponding coordinates of the first target cell on the first image and the second corresponding coordinates of the second target cell on the first image is less than the preset distance threshold, it can be determined that the first target cell and the second target cell correspond to the same target cell on the first image, that is, the first target cell and the second target cell are target cells that are photographed repeatedly.

[0057] In one embodiment, the image analysis device 200 can obtain the reference position coordinates of the target cell on the first image, the first position coordinates of the first target cell on the second image on the second image, and the second position coordinates of the second target cell on the third image on the third image, obtain the first corresponding coordinates of the first target cell on the first image based on the first corresponding position and the first position coordinates, and obtain the second corresponding coordinates of the second target cell on the first image based on the second corresponding position and the second position coordinates, and when the first coordinate difference between the first corresponding coordinate and the reference position coordinates and the second coordinate difference between the second corresponding coordinate and the reference position coordinates are both less than a preset coordinate difference threshold, it is determined that the first target cell and the second target cell are target cells that are repeatedly photographed. Specifically, when the first coordinate difference between the first corresponding coordinate and the reference position coordinates is less than the preset coordinate difference threshold, it can be determined that the first target cell and the target cell on the first image are the same cell, and when the second coordinate difference between the second corresponding coordinate and the reference position coordinates is also less than the preset coordinate difference threshold, it can be determined that the second target cell and the target cell on the first image are also the same cell, thereby determining that the first target cell and the second target cell are target cells that are repeatedly photographed.

[0058] Exemplarily, the preset coordinate difference threshold may be set based on experience, such as 1 μm, 2 μm, 3 μm, etc., which is not limited in the present invention.

[0059] In one embodiment, the image analysis system 10 may further include an image display device (not shown), which is used to mark the identified repeatedly photographed target cells or non-repeatedly photographed target cells and output them for display.

[0060] When it is determined that the above-mentioned multiple images contain repeatedly photographed target cells, the image analysis device 200 is also used to: remove the repeatedly photographed target cells, and output an image containing only non-repeatedly photographed target cells to an image display device. Exemplarily, the image after removing the repeatedly photographed target cells can be directly output, or a small image of the non-repeatedly photographed target cells can be output after further processing. The image analysis device 200 can also mark the repeatedly photographed target cells in the image and output them. In one embodiment, if the image contains more than one non-repeatedly photographed target cell, the image analysis device 200 can further output an image of each non-repeatedly photographed target cell to the image display device, so that the user can observe the morphology of each target cell separately.

[0061] In one embodiment, the image analysis system 10 may further include a smear moving device 300, which is used to drive the smear to move relative to the imaging device 100, so that the imaging device 100 captures an image of cells in the sample to be tested in a specific area on the smear. When the image does not contain the target cell, that is, when the image of the target cell is not captured, the smear moving device 300 can drive the smear to move so that the target cell that is not captured is located within the field of view of the objective lens, thereby re-capturing the image of the target cell that is not captured.

[0062] In one embodiment, the image analysis system 10 may further include an alarm device (not shown) for issuing an alarm message when the number of repeatedly photographed target cells contained in the multiple images reaches a predetermined number or when the same target cell is repeatedly photographed multiple times. Exemplarily, the predetermined number may be 3, 4, 5, 6, etc., which is not limited in the present invention. Exemplarily, the multiple times may be 3 times, 4 times, etc., which is not limited in the present invention. Exemplarily, the alarm message may include information such as sound, light, and text, which is not limited in the present invention.

[0063] In one embodiment, the image analysis system 10 may further include a smear identification device, a smear clamping device, and a smear recovery device, wherein the smear identification device is used to identify the identity information of the smear, the smear clamping device is used to clamp the smear from the identification device to the smear moving device 300 for detection, and the smear recovery device is used to place the detected smear. In another embodiment, the image analysis system 10 may also include a smear basket loading device for loading a smear basket containing a smear to be tested, and a smear clamping device for clamping the smear to be tested in the smear basket loaded on the smear basket loading device to the smear identification device for identity information identification. It should be understood that the image analysis system 10 may also include other devices known in the art, and the present invention is not limited thereto.

[0064] Embodiment 2

[0065] This embodiment provides an image analysis system. Similar to the image analysis system in the first embodiment, the image analysis system may include an imaging device 100 and an image analysis device 200, etc., wherein the imaging device 100 may include a camera unit 120, except that:

[0066] The camera unit 120 shoots the target cells contained in the sample to be tested on the smear to obtain a first image and a second image, and obtains the first image information of the first image and the second image information of the second image. Wherein, the first image and the second image are used to represent any two images of the multiple images shot by the camera unit 120, and do not specifically refer to two images. Exemplarily, the first image and the second image can be obtained by shooting with the same objective lens, for example, both are shot with a high-power objective lens (for example, 100 times). Wherein, the first image and the second image can be images respectively focused on different target cells, but because there will be inaccurate positioning problems when positioning the target cells, it may cause the first image and the second image to contain repeated target cells. Exemplarily, the image information may include pixel information, feature information and other information of the image.

[0067] The image analysis device 200 is used to: obtain the position coordinates of the first target cell in the first image on the first image, analyze the first image information and the second image information, determine the corresponding position of the second image on the first image, and determine the corresponding coordinates of the second target cell in the second image on the first image based on the corresponding position. When the distance between the position coordinates and the corresponding coordinates is less than or equal to a preset distance threshold, it is determined that the first target cell and the second target cell are the same target cell, so that the first target cell and the second target cell are target cells that are repeatedly photographed. Among them, the corresponding position of the second image on the first image is the area of ​​the second image corresponding to the first image. Exemplarily, the corresponding position of the second image on the first image can be determined using the image registration algorithm as described above, which will not be repeated here.

[0068] Exemplarily, as described above, the preset distance threshold may be set to be approximately equal to the size of the target cell, such as about 5 μm, which is not limited in the present invention.

[0069] In one embodiment, the image analysis system may further include an image display device, and the image display device is used to mark and display the identified repeatedly photographed target cells or non-repeatedly photographed cells.

[0070] When it is determined that the above image contains repeatedly photographed target cells, the image analysis device 200 is also used to: remove the repeatedly photographed target cells, and output an image containing only non-repeatedly photographed target cells to an image display device. Exemplarily, the image after removing the repeatedly photographed target cells can be directly output, or a small image of the non-repeatedly photographed target cells can be output after further processing. The image analysis device 200 can also mark the repeatedly photographed target cells in the image and output them. In one embodiment, if the image contains more than one non-repeatedly photographed target cell, the image analysis device 200 can further output an image of each non-repeatedly photographed target cell to the image display device, so that the user can observe the morphology of each target cell separately.

[0071] In one embodiment, the image analysis system 10 may further include an alarm device (not shown) for issuing an alarm when the number of repeatedly photographed target cells contained in the multiple images reaches a predetermined number or when the same target cell is repeatedly photographed multiple times. Exemplarily, the predetermined number may be 3, 4, 5, 6, etc., which is not limited in the present invention. Exemplarily, the multiple times may be 3 times, 4 times, etc., which is not limited in the present invention. Exemplarily, the alarm information may include information such as sound, light, and text, which is not limited in the present invention.

[0072] Embodiment 3

[0073] This embodiment provides an image analysis system. Similar to the image analysis system in the first embodiment, the image analysis system may include an imaging device 100 and an image analysis device 200, etc., wherein the imaging device 100 may include a camera unit 120, except that:

[0074] The camera unit 120 is used to photograph the target cells contained in the sample to be tested on the smear to obtain a first image and a second image, and obtain first image information of the first image and second image information of the second image. Among them, the first image and the second image are used to represent any two images of the multiple images photographed by the camera unit 120, and do not specifically refer to two images. Exemplarily, the first image and the second image can be obtained by photographing twice using the same objective lens, for example, by photographing twice using a high-power objective lens (for example, 100 times, etc.), or by photographing twice using a low-power objective lens (for example, 10 times, etc.). Exemplarily, the image information may include pixel information, feature information, and other information of the image.

[0075] The image analysis device 200 is used to analyze the first image information and the second image information, determine the corresponding position of the second image on the first image, and when the degree of overlap between the corresponding position and the position of the first image is greater than or equal to a preset overlap threshold, determine that the first image and the second image are repeatedly shot images, so that the target cells on the first image and the second image are repeatedly shot target cells. Among them, the corresponding position of the second image on the first image is the area of ​​the first image to which the second image corresponds. Exemplarily, the corresponding position of the second image on the first image can be determined using the image registration algorithm as described above, which will not be repeated here. Among them, the degree of overlap between the corresponding position and the position of the first image is the degree of overlap between the corresponding position and the position of the first image, which can be expressed as a percentage or a decimal.

[0076] Exemplarily, the preset overlap threshold may be 96%, 97%, 98%, 99%, etc., which is not limited in the present invention.

[0077] In one embodiment, the image analysis system may further include an image display device, and the image display device is used to mark and display the identified repeatedly photographed target cells or non-repeatedly photographed cells.

[0078] When it is determined that the above-mentioned multiple images contain repeatedly photographed target cells, the image analysis device 200 is also used to: remove the repeatedly photographed target cells, and output an image containing only non-repeatedly photographed target cells to the image display device. Exemplarily, the second image after removing the repeatedly photographed target cells can be directly output, or a small image of the non-repeatedly photographed target cells can be output after further processing. The image analysis device 200 can also mark the repeatedly photographed target cells in the image and output them. In one embodiment, if the image contains more than one non-repeatedly photographed target cell, the image analysis device 200 can further output an image of each non-repeatedly photographed target cell to the image display device, so that the user can observe the morphology of each target cell separately.

[0079] In one embodiment, the image analysis system 10 may further include an alarm device (not shown) for issuing an alarm message when the number of repeatedly photographed target cells contained in the multiple images reaches a predetermined number. Exemplarily, the predetermined number may be 3, 4, 5, 6, etc., which is not limited in the present invention. Exemplarily, the multiple times may be 3 times, 4 times, etc., which is not limited in the present invention. Exemplarily, the alarm message may include information such as sound, light, and text, which is not limited in the present invention.

[0080] Embodiment 4

[0081] This embodiment provides a sample analysis system A, referring to Figure 7 , Figure 7FIG. 4 shows a schematic diagram of the structure of a sample analysis system A according to an embodiment of the present invention. Figure 7 As shown, the sample analysis system A may include a blood analysis device A100, a smear preparation device A200, an image analysis device A300, and a control device A400, etc. Among them, the blood analysis device A110 is used to perform routine blood tests on the sample to be tested, the smear preparation device A200 is used to prepare a smear of the sample to be tested, the image analysis device A300 is used to take and analyze images of cells in the sample to be tested on the smear, and the control device A400 is connected to the blood analysis device A100, the smear preparation device A200, and the image analysis device A300 in a communication manner, and is used to transmit data to each device. The sample analysis system A may also include a transmission track connecting each device and a feeding mechanism of each device, etc. The control device A400 may be electrically connected to the transmission track and the feeding mechanism, and is used to control the movement of the transmission track and the feeding mechanism. In order to avoid unnecessary ambiguity of the present invention, it will not be described in detail here.

[0082] The image analysis device A300 may be the image analysis system 10 according to the first embodiment of the present invention. The structure of the image analysis system 10 is described in detail in the first embodiment and will not be described in detail herein.

[0083] Embodiment 5

[0084] This embodiment provides a method for identifying duplicate cells in an image analysis system. Figure 8 , Figure 8 A flowchart showing the steps of a method 800 for identifying duplicate cells in an image analysis system according to an embodiment of the present invention is shown.

[0085] like Figure 8 As shown, method 800 may include the following steps:

[0086] Step S810: photograph the sample to be tested on the smear to obtain a first image, and obtain first image information of the first image; photograph the target cells in the sample to be tested on the smear to obtain multiple images, and obtain image information of each of the multiple images, wherein the multiple images include a second image and a third image, and the image information includes second image information of the second image and third image information of the third image.

[0087] Exemplarily, the sample to be tested may be a blood sample, etc. Exemplarily, the target cells may be white blood cells, neutrophils, red blood cells, etc., which are not limited in the present invention.

[0088] Exemplarily, the first image can be obtained by taking a picture using a first objective lens. Exemplarily, the first objective lens can be a low-power objective lens, such as a 10x objective lens, in which case the field of view of the first objective lens can be all samples to be tested, and the corresponding first image can include all target cells. Exemplarily, the image information can include pixel information, feature information, and other information of the image.

[0089] Exemplarily, the plurality of images can be obtained by photographing using a second objective lens. Exemplarily, the second objective lens can be a high-power objective lens, such as a 100-power objective lens, and the second objective lens can be used to photograph each target cell in the sample to be tested one by one, thereby obtaining a plurality of images. Exemplarily, the image information of each image can include pixel information, feature information, and other information of each image.

[0090] The multiple images may include a second image, a third image, a fourth image, .... Accordingly, the image information may include second image information, third image information, fourth image information, .... The second, third, fourth, ... are only used to distinguish different images and corresponding image information in the multiple images, and do not specifically refer to a certain image or a certain image information.

[0091] Since the first image is taken with a low-power objective lens, its field of view is all the samples to be tested on the entire smear, and therefore all target cells can be included in the first image; and when each of the multiple images is taken with a high-power objective lens, its field of view is a small area on the smear where a target cell is located, and therefore the second image, the third image, etc. can include one cell to be tested, and when two or three cells are close to each other, they can also include two or three cells.

[0092] Step S820: Analyze the second image information, the third image information and the first image information respectively to determine a first corresponding position of the second image on the first image and a second corresponding position of the third image on the first image.

[0093] The first corresponding position and the second corresponding position refer to the areas on the first image to which the second image and the third image correspond respectively.

[0094] Exemplarily, an image registration algorithm may be used to analyze the second image information, the third image information and the first image information respectively to determine the first corresponding position of the second image on the first image and the second corresponding position of the third image on the first image. It should be understood that other methods may also be used to determine the first corresponding position of the second image on the first image and the second corresponding position of the third image on the first image, and the present invention is not limited thereto.

[0095] Since the process of analyzing two images using an image registration algorithm to determine the corresponding position of one image on the other image is similar, the following is explained by taking the example of analyzing the second image information and the first image information using an image registration algorithm to determine the first corresponding position of the second image on the first image.

[0096] Exemplarily, using an image registration algorithm to analyze the second image information and the first image information, determining the first corresponding position of the second image on the first image may include: extracting pixel information or feature information from the first image information and the second image information, and determining the first corresponding position of the second image on the first image based on the pixel information or feature information. Exemplarily, the algorithm for determining the corresponding position of the image based on pixel information may include the mean absolute difference algorithm (MAD), the absolute error sum algorithm (SAD), the error square sum algorithm (SSD), the mean error square sum algorithm (MSD), the normalized product correlation algorithm (NCC), the sequential similarity detection algorithm (SSDA), the hadamard transform algorithm (SATD), the local gray value encoding algorithm, etc. Specifically, the method for determining the corresponding position of the image based on feature information may include: first extracting the features of the image, then generating a feature descriptor, and finally matching the features of the two images according to the similarity of the descriptors. Among them, the features of the image can be mainly divided into features such as points, lines (edges), and regions (surfaces), and can also be divided into local features and global features. Exemplarily, methods for determining the corresponding positions of images based on point features may include Harris, Harr-like, HOG, LBP, SIFT and other algorithms, and methods for determining the corresponding positions of images based on edge features may include LoG operator, Robert operator, Sobel operator, Prewitt operator, Canny operator and the like.

[0097] Exemplarily, determining the first corresponding position of the second image on the first image based on pixel information may include: establishing a similarity measurement index using pixel information of both the first image and the second image, and determining the first corresponding position of the second image on the first image based on the similarity measurement index.

[0098] In order to improve the discrimination of the similarity metric, method 800 may include: establishing a similarity metric based on the average pixel values ​​of the second image and the first image. For example, the similarity metric γ may be established using the following formula:

[0099]

[0100] Among them, x and y are the coordinates of the pixel points respectively, and f(x, y) is the pixel value of each pixel point in a certain area on the first image. is the average pixel value of all pixels in the area on the first image, g(x,y) is the pixel value of each pixel on the second image, is the average pixel value of all pixels on the second image. It should be understood that f(x, y) can also be used. Represent the second image, using g(x,y), The formula of the present invention can improve the discrimination of the similarity measurement index and better distinguish the target cells in the second image in the first image.

[0101] Exemplarily, a sliding window method may be used to determine the value of the similarity measurement index, thereby determining the first corresponding position of the second image on the first image.

[0102] Specifically, the sliding window method may include: setting a sliding window so that the sliding window slides along a predetermined path on the first image, wherein the size of the sliding window is the same as the size of the second image; during the sliding process of the sliding window, calculating in real time the value of a similarity measurement index between the second image and the area of ​​the first image located within the sliding window; selecting the maximum value of the similarity measurement index, and the area of ​​the first image within the sliding window corresponding to the maximum value is the first corresponding position of the second image on the first image.

[0103] In one embodiment, the predetermined path may include a path from left to right and from top to bottom on the first image. In another embodiment, the predetermined path may include It should be understood that the predetermined path may also be other suitable paths, and the present invention is not limited thereto.

[0104] When the shooting field of the second image is at the edge of the shooting field of the first image, there will be an edge problem, which makes the value of the correlation metric index low, so that the correct corresponding position cannot be found. Therefore, in one embodiment, if the sliding window is partially located outside the first image, method 800 may include: calculating the value of the similarity metric index based on a preset overlap threshold.

[0105] Specifically, if the ratio of the area of ​​the overlapping part of the sliding window and the first image to the total area of ​​the sliding window is greater than or equal to the overlap threshold, it indicates that most of the sliding window is in the first image at this time, and the method 800 may include: calculating the value of the similarity measurement index between the part of the first image that overlaps with the sliding window and the corresponding part of the second image. If the ratio of the area of ​​the overlapping part of the sliding window and the first image to the total area of ​​the sliding window is less than the overlap threshold, it indicates that only a small part of the sliding window is in the first image at this time, and the overlapping area of ​​the field of view of the two images is very small, and the accuracy of the similarity measurement index is low, so the method 800 may include: calculating the similarity measurement index as zero. Among them, the overlap threshold can be set according to experience, for example, it can be set to 0.6-0.8, etc., and the present invention is not limited to this.

[0106] Before analyzing the first image and the second image using the sliding window method, the first image and the second image need to be preprocessed.

[0107] Exemplarily, the preprocessing may include resampling the first image and / or the second image so that the resolution of the first image and the second image are the same, that is, the size represented by each pixel on the two images is the same. Resampling may include upsampling and downsampling. Exemplarily, the resolution of the first image may be kept unchanged, and the second image may be downsampled to the same resolution as the first image, or the resolution of the second image may be kept unchanged, and the first image may be upsampled to the same resolution as the second image, or the first image and the second image may be resampled to a certain resolution at the same time, and the present invention is not limited to this. The resampling method may adopt the nearest neighbor interpolation method, bilinear interpolation method, cubic convolution interpolation method, etc., which are well known in the art, and the present invention is not limited to this.

[0108] In order to reduce the amount of calculation, the preprocessing may also include converting both the first image and the second image into grayscale images before resampling the first image and / or the second image. The method of converting a color image into a grayscale image is well known and will not be described in detail here.

[0109] Since the value of the similarity metric index between the second image and the area of ​​the first image within the sliding window must be recalculated each time the sliding window slides one pixel, many positions need to be traversed, so the amount of calculation is very large. In order to optimize the operation speed, in one embodiment, method 800 may include: first converting the first image and the second image to the frequency domain, and then calculating the value of the similarity metric index between the second image and the area of ​​the first image within the sliding window. The method of converting the first image and the second image to the frequency domain may be the FFT (Fast Fourier Transform) method, etc., which will not be repeated here.

[0110] In order to optimize the operation speed, in another embodiment, method 800 may include: using the integral image method to calculate the value of the similarity metric between the second image and the area of ​​the first image located in the sliding window. First, an array may be constructed as an integral image, the width and height of the integral image being the same as those of the first image, and then the array is assigned a value, and the value of each point is the sum of the pixel values ​​of all the pixel points in the coverage area from the upper left corner vertex of the first image to the point; then the integral image can be used to conveniently calculate the sum of the pixel values ​​of all the pixel points in the sliding window, and then the value of the similarity metric between the second image and the area of ​​the first image located in the sliding window can be conveniently calculated.

[0111] Step S830: When the distance between the first corresponding position and the second corresponding position is less than or equal to the preset distance threshold, the target cells in the second image and the third image are determined to be repeatedly photographed target cells. That is, if the distance between the first area on the first image corresponding to the second image and the second area on the first image corresponding to the third image is less than or equal to the preset distance threshold, the second image and the third image are determined to be repeatedly photographed images, so that the target cells in the second image and the third image are repeatedly photographed target cells.

[0112] Exemplarily, the preset distance threshold may be set to be approximately equal to the size of the target cell, such as about 5 μm, which is not limited in the present invention.

[0113] Exemplarily, the method 800 may further include: based on the first corresponding position of the second image on the first image and the second corresponding position of the third image on the first image, respectively obtaining the first corresponding coordinates and the second corresponding coordinates of the first target cell on the second image and the second target cell on the third image on the first image. Specifically, the coordinates of the first target cell on the second image may be obtained, and the coordinates may be combined with the first corresponding position to obtain the first corresponding coordinates of the first target cell on the first image, and a similar method may be used to obtain the second corresponding coordinates of the second target cell on the first image. Then, the method 800 may further include: when the distance between the first corresponding coordinates and the second corresponding coordinates is less than or equal to a preset distance threshold, determining that the first target cell and the second target cell are target cells that are repeatedly photographed.

[0114] Exemplarily, as described above, the preset distance threshold can be set to be approximately equal to the size of the target cell, for example, about 5 μm. At this time, if the distance between the first corresponding coordinates of the first target cell on the first image and the second corresponding coordinates of the second target cell on the first image is less than the preset distance threshold, it can be determined that the first target cell and the second target cell correspond to the same target cell on the first image, that is, the first target cell and the second target cell are target cells that are photographed repeatedly.

[0115] Exemplarily, the method 800 may further include: obtaining the reference position coordinates of the target cell on the first image, the first position coordinates of the first target cell on the second image on the second image, and the second position coordinates of the second target cell on the third image on the third image, obtaining the first corresponding coordinates of the first target cell on the first image based on the first corresponding position and the first position coordinates, and obtaining the second corresponding coordinates of the second target cell on the first image based on the second corresponding position and the second position coordinates, and when the first coordinate difference between the first corresponding coordinate and the reference position coordinates and the second coordinate difference between the second corresponding coordinate and the reference position coordinates are both less than a preset coordinate difference threshold, then determining that the first target cell and the second target cell are target cells that are repeatedly photographed. Specifically, when the first coordinate difference between the first corresponding coordinate and the reference position coordinates is less than the preset coordinate difference threshold, then determining that the first target cell and the target cell on the first image are the same cell, and when the second coordinate difference between the second corresponding coordinate and the reference position coordinates is also less than the preset coordinate difference threshold, then determining that the second target cell and the target cell on the first image are also the same cell, thereby determining that the first target cell and the second target cell are target cells that are repeatedly photographed.

[0116] Exemplarily, the preset coordinate difference threshold may be set based on experience, such as 1 μm, 2 μm, 3 μm, etc., which is not limited in the present invention.

[0117] When it is determined that the above-mentioned multiple images contain repeatedly photographed target cells, method 800 may further include: marking the identified repeatedly photographed target cells or non-repeatedly photographed target cells, and outputting them for display. Method 800 may further include: removing the repeatedly photographed target cells, and outputting an image containing only non-repeatedly photographed target cells to an image display device. Exemplarily, the image after removing the repeatedly photographed target cells can be directly output, or a small image of the non-repeatedly photographed target cells can be output after further processing. Method 800 may further include: marking the repeatedly photographed target cells in the image and outputting them. In one embodiment, if the image contains more than one non-repeatedly photographed target cells, method 800 may further include: outputting an image for each non-repeatedly photographed target cell, so that the user can observe the morphology of each target cell separately.

[0118] In one embodiment, when the target cells are not included in the image, that is, when the image of the target cells is not captured, method 800 may further include: moving the smear so that the uncaptured target cells are located within the field of view of the objective lens, thereby re-capturing the image of the uncaptured target cells.

[0119] In one embodiment, method 800 may further include: issuing an alarm message when the number of repeatedly photographed target cells contained in the multiple images reaches a predetermined number or the same target cell is repeatedly photographed multiple times. Exemplarily, the predetermined number may be 3, 4, 5, 6, etc., which is not limited in the present invention. Exemplarily, the multiple times may be 3 times, 4 times, etc., which is not limited in the present invention. Exemplarily, the alarm message may include information such as sound, light, and text, which is not limited in the present invention.

[0120] Embodiment 6

[0121] This embodiment provides a method for an image analysis system to identify duplicate cells. Fig. 9 , Fig. 9 A flowchart showing the steps of a method 900 for identifying duplicate cells in an image analysis system according to another embodiment of the present invention is shown.

[0122] like Fig. 9 As shown, method 900 may include the following steps:

[0123] Step S910: photographing the target cells contained in the sample to be tested on the smear to obtain a first image and a second image, obtaining first image information of the first image and second image information of the second image, and obtaining the position coordinates of the first target cell in the first image on the first image.

[0124] Exemplarily, the sample to be tested may be a blood sample, etc. Exemplarily, the target cells may be white blood cells, neutrophils, red blood cells, etc., which are not limited in the present invention.

[0125] Wherein, the first image and the second image are used to represent any two images of the plurality of images taken, and do not specifically refer to two images. Exemplarily, the first image and the second image can be obtained by taking pictures by the camera unit using the same objective lens, for example, both are taken using a high-power objective lens (for example, 100 times). Wherein, the first image and the second image can be images taken by focusing on different target cells respectively, but since there is a problem of inaccurate positioning when positioning the target cells, it may cause the first image and the second image to contain target cells that are repeatedly photographed.

[0126] Exemplarily, the image information may include pixel information, feature information, and other information of the image.

[0127] Step S920: Analyze the first image information and the second image information to determine the corresponding position of the second image on the first image.

[0128] The corresponding position of the second image on the first image refers to the area of ​​the first image to which the second image corresponds.

[0129] Exemplarily, the corresponding position of the second image on the first image may be determined using the image registration algorithm described above, which will not be described in detail herein.

[0130] Step S930: Based on the corresponding position, determine the corresponding coordinates of the second target cell in the second image on the first image, and when the distance between the position coordinates and the corresponding coordinates is less than or equal to a preset distance threshold, determine that the first target cell and the second target cell are target cells that are repeatedly photographed.

[0131] Specifically, when the distance between the position coordinate and the corresponding coordinate is less than or equal to a preset distance threshold, it can be determined that the first target cell and the second target cell are the same target cell, so that the first target cell and the second target cell are target cells that are repeatedly photographed.

[0132] Exemplarily, as described above, the preset distance threshold may be set to be approximately equal to the size of the target cell, such as about 5 μm, which is not limited in the present invention.

[0133] Illustratively, when it is determined that the above image contains repeatedly photographed target cells, method 900 may further include: marking the identified repeatedly photographed target cells or non-repeatedly photographed target cells, and outputting them for display.

[0134] Method 900 may further include: removing the repeatedly photographed target cells and outputting an image containing only the non-repeatedly photographed target cells. Exemplarily, the image after removing the repeatedly photographed target cells may be directly output, or a small image of the non-repeatedly photographed target cells may be output after further processing.

[0135] Method 900 may further include: marking the repeatedly photographed target cell in the image and outputting it. In one embodiment, if the image contains more than one non-repeatedly photographed target cell, method 900 may further include: outputting an image for each non-repeatedly photographed target cell, so that the user can observe the morphology of each target cell separately.

[0136] In one embodiment, method 900 may further include: issuing an alarm message when the number of repeatedly photographed target cells contained in the image reaches a predetermined number or the same target cell is repeatedly photographed multiple times. Exemplarily, the predetermined number may be 3, 4, 5, 6, etc., which is not limited in the present invention. Exemplarily, the multiple times may be 3 times, 4 times, etc., which is not limited in the present invention. Exemplarily, the alarm message may include information such as sound, light, and text, which is not limited in the present invention.

[0137] Embodiment 7

[0138] This embodiment provides a method for an image analysis system to identify duplicate cells. Fig.10 , Fig.10 A flowchart of a method 1000 for identifying duplicate cells in an image analysis system according to another embodiment of the present invention is shown.

[0139] like Fig.10 As shown, method 1000 may include the following steps:

[0140] Step S1010: photographing target cells contained in the sample to be tested on the smear to obtain a first image and a second image, and obtaining first image information of the first image and second image information of the second image.

[0141] Exemplarily, the sample to be tested may be a blood sample, etc. Exemplarily, the target cells may be white blood cells, neutrophils, red blood cells, etc., which are not limited in the present invention.

[0142] The first image and the second image are used to represent any two images among the multiple images taken, and do not specifically refer to two images. For example, the first image and the second image can be obtained by taking two images in succession using the same objective lens, such as taking two images in succession using a high-power objective lens (e.g., 100 times, etc.), or taking two images in succession using a low-power objective lens (e.g., 10 times, etc.).

[0143] Exemplarily, the image information may include pixel information, feature information, and other information of the image.

[0144] Step S1020: Analyze the first image information and the second image information to determine the corresponding position of the second image on the first image.

[0145] The corresponding position of the second image on the first image refers to the area of ​​the first image to which the second image corresponds.

[0146] Exemplarily, the corresponding position of the second image on the first image may be determined using the image registration algorithm described above, which will not be described in detail herein.

[0147] Step S1030: When the degree of overlap between the corresponding position and the position of the first image is greater than or equal to the overlap threshold, the first image and the second image are determined to be repeatedly shot images, so that the target cells in the first image and the second image are repeatedly shot target cells.

[0148] The degree of coincidence between the corresponding position and the position of the first image is the degree of coincidence between the corresponding position and the position of the first image, which can be expressed as a percentage or a decimal.

[0149] Exemplarily, the preset overlap threshold may be 96%, 97%, 98%, 99%, etc., which is not limited in the present invention.

[0150] Illustratively, when it is determined that the above image contains repeatedly photographed target cells, method 1000 may further include: marking the identified repeatedly photographed target cells or non-repeatedly photographed target cells, and outputting them for display.

[0151] Method 1000 may further include: removing the repeatedly photographed target cells and outputting an image containing only the non-repeatedly photographed target cells. Exemplarily, the image after removing the repeatedly photographed target cells may be directly output, or a small image of the non-repeatedly photographed target cells may be output after further processing.

[0152] Method 1000 may further include: marking the repeatedly photographed target cell in the image and outputting the mark. In one embodiment, if the image contains more than one non-repeatedly photographed target cell, method 1000 may further include: outputting an image for each non-repeatedly photographed target cell, so that the user can observe the morphology of each target cell.

[0153] In one embodiment, method 1000 may further include: issuing an alarm message when the number of repeatedly photographed target cells contained in the image reaches a predetermined number or the same target cell is repeatedly photographed multiple times. Exemplarily, the predetermined number may be 3, 4, 5, 6, etc., which is not limited in the present invention. Exemplarily, the multiple times may be 3 times, 4 times, etc., which is not limited in the present invention. Exemplarily, the alarm message may include information such as sound, light, and text, which is not limited in the present invention.

[0154] Embodiment 8

[0155] The present embodiment provides a computer-readable medium, on which a computer program is stored, and the computer program executes the method for identifying repeated cells for an image analysis system as described in the above embodiment when it is run. Any tangible, non-temporary computer-readable medium can be used, including magnetic storage devices (hard disks, floppy disks, etc.), optical storage devices (CD-ROMs, DVDs, Blu-ray discs, etc.), flash memory and / or the like. These computer program instructions can be loaded onto a general-purpose computer, a special-purpose computer, or other programmable data processing device to form a machine, so that these instructions executed on a computer or other programmable data processing device can generate a device that implements a specified function. These computer program instructions can also be stored in a computer-readable memory, which can instruct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory can form a manufactured product, including an implementation device that implements a specified function. The computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operating steps are performed on the computer or other programmable device to generate a computer-implemented process, so that the instructions executed on the computer or other programmable device can provide steps for implementing the specified function.

[0156] Technical effects of the present invention:

[0157] The image analysis system, the method for identifying duplicate cells in the image analysis system, the sample analysis system and the computer-readable medium of the embodiments of the present invention can identify duplicate cells and determine whether the target cells are photographed by determining the corresponding position of one image on another image. This can be achieved using the existing system without the need for additional devices, and the recognition process has a small amount of computational complexity and can solve the edge matching problem.

[0158] Although example embodiments have been described herein with reference to the accompanying drawings, it should be understood that the above example embodiments are merely exemplary and are not intended to limit the scope of the present invention thereto. Various changes and modifications may be made therein by one of ordinary skill in the art without departing from the scope and spirit of the present invention. All such changes and modifications are intended to be included within the scope of the present invention as required by the appended claims.

[0159] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0160] Similarly, it should be understood that in order to streamline the present invention and help understand one or more of the various inventive aspects, in the description of the exemplary embodiments of the present invention, the various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, the method of the present invention should not be interpreted as reflecting the following intention: the claimed invention requires more features than the features explicitly stated in each claim. More specifically, as reflected in the corresponding claims, the inventive point is that the corresponding technical problem can be solved with less than all the features of a single disclosed embodiment. Therefore, the claims following the specific embodiment are hereby expressly incorporated into the specific embodiment, wherein each claim itself serves as a separate embodiment of the present invention.

[0161] It will be understood by those skilled in the art that, except for mutually exclusive features, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this specification may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature that provides the same, equivalent or similar purpose.

[0162] In addition, those skilled in the art will appreciate that, although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present invention and form different embodiments. For example, in the claims, any one of the claimed embodiments may be used in any combination.

[0163] It should be noted that the above embodiments illustrate the present invention rather than limit it, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be construed as a limitation on the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising a number of different elements and by means of a suitably programmed computer. In a unit claim enumerating a number of devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc., does not indicate any order. These words may be interpreted as names.

[0164] The above is only a specific embodiment of the present invention or an explanation of a specific embodiment. The protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. The protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. An image analysis system, characterized in that: The image analysis system comprises an imaging device and an image analysis device, wherein: The imaging device comprises an imaging unit, wherein the imaging unit photographs the sample to be tested on the smear to obtain a first image, and obtains first image information of the first image; the imaging unit photographs a plurality of target cells in the sample to be tested on the smear one by one to obtain a plurality of images, and obtains image information of each of the plurality of images, wherein the plurality of images comprises a second image and a third image, wherein the second image and the third image are obtained by sequentially photographing the same sample to be tested, and the image information comprises second image information of the second image and third image information of the third image; The image analysis device is used for: Analyze the second image information, the third image information and the first image information respectively to determine a first corresponding position of the second image on the first image and a second corresponding position of the third image on the first image; When the distance between the first corresponding position and the second corresponding position is less than or equal to a preset distance threshold, it is determined that the target cells in the second image and the third image are target cells that are photographed repeatedly.

2. The image analysis system according to claim 1, characterized in that: The image analysis device is also used for: Based on the first corresponding position and the second corresponding position, respectively acquiring first corresponding coordinates and second corresponding coordinates of a first target cell on the second image and a second target cell on the third image on the first image; When the distance between the first corresponding coordinate and the second corresponding coordinate is less than or equal to the preset distance threshold, it is determined that the first target cell and the second target cell are target cells that are photographed repeatedly.

3. The image analysis system according to claim 1, characterized in that: The image analysis device is also used for: Acquire the reference position coordinates of the target cell on the first image, the first position coordinates of the first target cell on the second image on the second image, and the second position coordinates of the second target cell on the third image on the third image; Acquire a first corresponding coordinate of the first target cell on the first image based on the first corresponding position and the first position coordinate, and acquire a second corresponding coordinate of the second target cell on the first image based on the second corresponding position and the second position coordinate; When a first coordinate difference between the first corresponding coordinate and the reference position coordinate and a second coordinate difference between the second corresponding coordinate and the reference position coordinate are both smaller than a preset coordinate difference threshold, it is determined that the first target cell and the second target cell are target cells that are photographed repeatedly.

4. The image analysis system according to any one of claims 1 to 3, characterized in that: The image analysis device is also used to: use an image registration algorithm to analyze the second image information, the third image information and the first image information respectively, and determine a first corresponding position of the second image on the first image and a second corresponding position of the third image on the first image.

5. The image analysis system according to claim 4, characterized in that: The image analysis device uses an image registration algorithm to analyze the second image information and the first image information to determine a first corresponding position of the second image on the first image, including: Pixel information or feature information is extracted from the first image information and the second image information, and a first corresponding position of the second image on the first image is determined based on the pixel information or the feature information.

6. The image analysis system according to claim 5, characterized in that: The image analysis device determines the first corresponding position of the second image on the first image based on the pixel information, including: establishing a similarity measurement index using the pixel information of both the first image and the second image, and determining the first corresponding position of the second image on the first image based on the similarity measurement index.

7. The image analysis system according to claim 6, characterized in that: The image analysis device determines the first corresponding position of the second image on the first image based on the similarity measurement index, including: using a sliding window method to determine the value of the similarity measurement index, thereby determining the first corresponding position of the second image on the first image.

8. The image analysis system according to claim 7, characterized in that: The image analysis device uses a sliding window method to determine the value of the similarity measurement index, thereby determining a first corresponding position of the second image on the first image, including: Preprocessing the first image and the second image, wherein the preprocessing includes resampling the first image and / or the second image so that the first image and the second image have the same resolution; Setting a sliding window so that the sliding window slides along a predetermined path on the first image, wherein the size of the sliding window is the same as the size of the second image; During the sliding process of the sliding window, calculating in real time the value of the similarity measurement index of the second image and the area of ​​the first image located within the sliding window; A maximum value among the values ​​of the similarity measurement index is selected, and the area of ​​the first image in the sliding window corresponding to the maximum value is the first corresponding position of the second image on the first image.

9. The image analysis system according to any one of claims 1 to 8, characterized in that: The image analysis system further comprises an image display device, which is further used to mark the identified repeatedly photographed target cells or non-repeatedly photographed target cells, and output them for display.

10. The image analysis system according to claim 9, characterized in that: The image analysis device is also used to remove the target cells that are photographed repeatedly, and output an image containing only the target cells that are not photographed repeatedly to the image display device.

11. The image analysis system according to any one of claims 1 to 10, characterized in that: The image analysis system further comprises an alarm device, which is used to issue an alarm message when the number of repeatedly photographed target cells contained in the second image reaches a predetermined number or the same target cell is photographed repeatedly for multiple times.

12. An image analysis system, characterized in that: The image analysis system comprises an imaging device and an image analysis device, wherein: The imaging device comprises an imaging unit, which photographs target cells contained in the sample to be tested on the smear one by one to obtain a first image and a second image, and obtains first image information of the first image and second image information of the second image, wherein the first image and the second image are obtained by respectively focusing on different target cells using the same objective lens; The image analysis device is used for: Acquire the position coordinates of the first target cell in the first image on the first image; Analyze the first image information and the second image information to determine a corresponding position of the second image on the first image; Based on the corresponding position, the corresponding coordinates of the second target cell in the second image on the first image are determined, and when the distance between the position coordinates and the corresponding coordinates is less than or equal to a preset distance threshold, it is determined that the first target cell and the second target cell are target cells that are photographed repeatedly.

13. The image analysis system according to claim 12, characterized in that: The image analysis system further comprises an image display device, which is used to mark and display the identified repeatedly photographed target cells or non-repeatedly photographed target cells.

14. The image analysis system according to claim 13, characterized in that: The image analysis device is also used to remove the target cells that are photographed repeatedly, and output an image containing only the target cells that are not photographed repeatedly to the image display device.

15. The image analysis system according to any one of claims 12 to 14, characterized in that: The image analysis system further comprises an alarm device, which is used to issue an alarm message when the number of repeatedly photographed target cells contained in the second image reaches a predetermined number or the same target cell is photographed repeatedly for multiple times.

16. An image analysis system, characterized in that: The image analysis system comprises an imaging device and an image analysis device, wherein: The imaging device comprises an imaging unit, which photographs target cells contained in the sample to be tested on the smear one by one to obtain a first image and a second image, and obtains first image information of the first image and second image information of the second image, wherein the first image and the second image are obtained by photographing different target cells twice in succession using the same objective lens; The image analysis device is used for: Analyze the first image information and the second image information to determine a corresponding position of the second image on the first image; When the degree of overlap between the corresponding position and the position of the first image is greater than or equal to a preset overlap threshold, it is determined that the first image and the second image are repeatedly shot images, so that the target cells in the first image and the second image are repeatedly shot target cells.

17. The image analysis system according to claim 16, characterized in that: The image analysis system further includes an image display device, which is used to mark and display the identified repeatedly shot images.

18. The image analysis system according to claim 17, characterized in that: The image analysis device is also used to remove the repeatedly shot images and output only the non-repeatedly shot images to the image display device.

19. The image analysis system according to any one of claims 16 to 18, characterized in that: The image analysis system further comprises an alarm device, which is used to issue an alarm message when the number of the repeatedly photographed images reaches a predetermined number.

20. A sample analysis system, comprising a blood analysis device, a smear preparation device, an image analysis device and a control device, characterized in that: The image analysis device comprises the image analysis system according to any one of claims 1-19.

21. A method for identifying duplicate cells using an image analysis system, characterized in that: The method comprises: photographing the sample to be tested on the smear to obtain a first image, and obtaining first image information of the first image; photographing multiple target cells in the sample to be tested on the smear one by one to obtain multiple images, and obtaining image information of each of the multiple images, wherein the multiple images include a second image and a third image, wherein the second image and the third image are obtained by photographing the same sample to be tested in sequence, and the image information includes second image information of the second image and third image information of the third image; Analyze the second image information, the third image information and the first image information respectively to determine a first corresponding position of the second image on the first image and a second corresponding position of the third image on the first image; When the distance between the first corresponding position and the second corresponding position is less than or equal to a preset distance threshold, it is determined that the target cells in the second image and the third image are repeatedly photographed target cells.

22. The method according to claim 21, characterized in that The method further comprises: Based on the first corresponding position and the second corresponding position, respectively acquiring first corresponding coordinates and second corresponding coordinates of a first target cell on the second image and a second target cell on the third image on the first image; When the distance between the first corresponding coordinate and the second corresponding coordinate is less than or equal to the preset distance threshold, it is determined that the first target cell and the second target cell are target cells that are photographed repeatedly.

23. The method according to claim 21, characterized in that The method further comprises: Acquire the reference position coordinates of the target cell on the first image, the first position coordinates of the first target cell on the second image on the second image, and the second position coordinates of the second target cell on the third image on the third image; Acquire a first corresponding coordinate of the first target cell on the first image based on the first corresponding position and the first position coordinate, and acquire a second corresponding coordinate of the second target cell on the first image based on the second corresponding position and the second position coordinate; When a first coordinate difference between the first corresponding coordinate and the reference position coordinate and a second coordinate difference between the second corresponding coordinate and the reference position coordinate are both smaller than a preset coordinate difference threshold, it is determined that the first target cell and the second target cell are target cells that are photographed repeatedly.

24. A method for identifying duplicate cells using an image analysis system, characterized in that: The method comprises: photographing different target cells contained in the sample to be tested on the smear one by one to obtain a first image and a second image in sequence, obtaining first image information of the first image and second image information of the second image, and obtaining position coordinates of a first target cell in the first image on the first image; Analyze the first image information and the second image information to determine a corresponding position of the second image on the first image; Based on the corresponding position, the corresponding coordinates of the second target cell in the second image on the first image are determined, and when the distance between the position coordinates and the corresponding coordinates is less than or equal to a preset distance threshold, it is determined that the first target cell and the second target cell are target cells that are photographed repeatedly.

25. A method for identifying duplicate cells using an image analysis system, characterized in that: The method comprises: Photographing different target cells contained in the sample to be tested on the smear one by one to obtain a first image and a second image in sequence, and acquiring first image information of the first image and second image information of the second image; Analyze the first image information and the second image information to determine a corresponding position of the second image on the first image; When the degree of overlap between the corresponding position and the position of the first image is greater than or equal to a degree of overlap threshold, it is determined that the first image and the second image are repeatedly shot images, so that the target cells in the first image and the second image are repeatedly shot target cells.

26. A computer-readable storage medium comprising computer-executable instructions, characterized in that: When the computer executable instructions are executed by a processor, the method for identifying duplicate cells by an image analysis system according to any one of claims 21 to 25 can be performed.

Images