Blood cell detection method based on microscopic image processing

Abstract

The invention discloses a blood cell detection method based on microscopic image processing. The method comprises the following steps: dropping a blood sample on a slide and making a blood smear; a microscopic image of the whole blood smear view is collected through a microscope; and processing the microscopic image to obtain the characteristics of the cell microscopic image. According to the method, blood cell detection is conveniently carried out in a mode of manufacturing the blood smear, and the microscopic image of the blood smear is collected by adopting the microscope to obtain the microscopic image characteristics of the cells, so that the structural characteristics of the blood cells on the blood smear can be truly restored, and the detection of the blood cells is realized.

Description

Technical Field

[0001] The invention belongs to the field of microscopic image processing, and in particular relates to a blood cell detection method based on microscopic image processing. Background Art

[0002] Microscopic examination of blood smears is a basic method for blood cytology examination and is widely used. However, in clinical practice, it is difficult for existing technologies to directly capture clear cell images of blood smears. Three-dimensional cells are mostly focused by cross-sectional cutting and scanning after focusing the microscope. In the prior art, it is necessary to perform layered cutting on each area of ​​the objective lens field of view of the blood smear, and use the hill climbing method to continuously determine the clear layers of each area of ​​the objective lens field of view, and then perform splicing and imaging of clear images. This method can effectively present clear cell images, but it requires strong computing power and storage as support. At the same time, the image scanning process is time-consuming and inefficient, thus limiting the imaging speed. Summary of the invention

[0003] In view of the above-mentioned deficiencies in the prior art, the technical problem to be solved by the present invention is to provide a blood cell detection method based on microscopic image processing.

[0004] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0005] A blood cell detection method based on microscopic image processing comprises the following steps:

[0006] S100, dropping a blood sample on a glass slide and making a blood smear;

[0007] S200, collecting a microscopic image of the entire blood smear field of view through a microscope;

[0008] S300, processing the microscopic image to obtain cell microscopic image features.

[0009] Furthermore, the step S100 includes the following sub-steps:

[0010] S101, take two glass slides, one of which is used as a slide glass and the other is used as a push slide;

[0011] S102, placing the glass slide horizontally, and dropping a drop of blood sample on one end of the glass slide to form a blood drop;

[0012] S103, making the pusher slide and the glass slide form an angle of 15° to 45° in front of the blood drop and slowly approaching the blood drop;

[0013] S104, when one end of the push sheet contacts the blood drop, so that the blood drop spreads to a proper width along the edge of the push sheet, the push sheet is lightly pressed and quickly pushed in the opposite direction, so that the blood drop is evenly dragged on the slide to form a blood film;

[0014] S105, after the blood film is dried, staining the blood film to obtain a blood smear.

[0015] Furthermore, the step S200 includes the following sub-steps:

[0016] S201, establishing a spatial rectangular coordinate system with the blood smear plane as the XOY plane and the elevation direction as the Z axis direction;

[0017] S202, determining a scanning path of the microscope, taking a single field of view of the microscope as a unit of scanning area, and scanning the blood smear along the scanning path;

[0018] S203, photographing the first unit scanning area of ​​the scanning path with a microscope, dividing the focus area of ​​the microscope into n layers along the Z-axis direction, identifying the layer image with the highest definition along the Z-axis direction as the microscopic image of the first unit scanning area by a hill climbing method, and calculating the Z-axis coordinate of the layer image as the standard layer Z coordinate of the second unit scanning area;

[0019] S204, photographing the next unit scanning area of ​​the scanning path using a microscope, and dividing 2m+1 layers along the Z axis direction based on the standard layer Z coordinate of the unit scanning area, 2m+1<n;

[0020] S205, identifying the layer image with the highest definition from the 2m+1 layer images as the microscopic image of the unit scanning area, and calculating the Z-axis coordinate of the layer image as the standard layer Z coordinate of the next unit scanning area;

[0021] S206. Repeat steps S204 and S205 to obtain microscopic images of each unit scanning area of ​​the blood smear, and stitch them together to obtain a microscopic image of the entire blood smear field of view.

[0022] Furthermore, in the step S201, a corner point of the blood smear is taken as the origin of the spatial rectangular coordinate system, and the length direction and width direction of the blood smear are taken as the X-axis direction and Y-axis direction of the XOY plane respectively; in the step S202, when scanning the blood smear, a "battlement-like" movement method is used in the X-axis direction and the Y-axis direction to determine the scanning path of the microscope.

[0023] Furthermore, in the step S204, the method of dividing the focus area of ​​the recognition image into 2m+1 layers along the Z axis direction based on the Z coordinate of the standard layer is:

[0024] Take the Z coordinate of the standard layer as the standard layer, start from the standard layer and step upward with a predetermined step value and divide it in sequence to form m layers, start from the standard layer and step downward with a predetermined step value and divide it in sequence to form m layers, and obtain 2m+1 layers including the standard layer.

[0025] Furthermore, the value of m is 2 or 3; and the predetermined step value is 50 nm to 500 nm.

[0026] Furthermore, in the step S203 and the step S205, after the layer image with the highest definition is identified, the microbubble positioning method is used to obtain the center position coordinates of the layer image as the image coordinates, and the Z coordinate in the center position coordinates is the standard layer Z coordinate of the next unit scanning area; in the step S206, the positions of each microscopic image are arranged according to the X coordinate and Y coordinate in the image coordinates, and splicing is performed.

[0027] Furthermore, in the step S205, the method for identifying the layer image with the highest definition is:

[0028] Presetting a convolutional neural network model for predicting the clarity of an image, and training the convolutional neural network model to obtain a clarity recognition model;

[0029] Each layer image is input into the clarity recognition model to obtain the clarity prediction value of each layer image, and the layer image with the highest clarity prediction value is output as the layer image with the highest clarity.

[0030] Furthermore, in the step S205, a definition factor calculation formula is used to calculate the definition factor of each layer image. The definition factor calculation formula is as follows:

[0031]

[0032] Where σ represents the clarity factor; N represents the number of all pixels in the area; x i represents the gray level of the i-th pixel; μ represents the average gray level of the image;

[0033] After calculating the clarity factor of each layer image, it is determined whether the layer image output by the clarity recognition model is consistent with the layer image with the largest clarity factor value. If they are inconsistent, the layer image output by the clarity recognition model is marked.

[0034] Furthermore, in the step S300, the acquired cell microscopic image features include cell edge shape, cell diameter, cell color, cell nucleus distribution and cell structure.

[0035] In the present invention, blood cell detection is facilitated by making a blood smear, and the method of collecting microscopic images of blood smears with a microscope is improved. When collecting microscopic images of blood smears, starting from the second unit scanning area, the layers of each area are divided into only 5 or 7 layers, from which the clearest image can be identified and screened, and the number of layers that need to be divided and the number of layer images identified after segmentation are greatly reduced, thereby greatly reducing the processing volume and the requirements for computing power, while improving the imaging speed, and can truly restore the structural characteristics of blood cells on the blood smear, and realize the detection of blood cells. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0037] Figure 1 FIG. 4 is a flow chart of an embodiment of a blood cell detection method based on microscopic image processing according to the present invention.

[0038] Figure 2 Flowchart for making a blood smear.

[0039] Figure 3 Schematic diagram of using the hill climbing method to identify the layer image with the highest clarity.

[0040] Figure 4 This is a schematic diagram of scanning the entire blood smear and splicing it to form a microscopic image of the entire blood smear field in this embodiment.

[0041] Figure 5 Schematic diagram of scanning the entire blood smear using the "battlement-style" movement method.

[0042] The accompanying drawings in the specification are as follows:

[0043] Blood smear-100; Single field of view area-200; First unit scanning area-201; Second unit scanning area-202; Scanning path-300. DETAILED DESCRIPTION

[0044] The following describes the implementation methods of the present invention through specific examples. The illustrations provided in the following embodiments are only used to schematically illustrate the basic concept of the present invention. The following embodiments and features in the embodiments may be combined with each other without conflict.

[0045] See also Figure 1 An embodiment of the blood cell detection method based on microscopic image processing of the present invention comprises the following steps:

[0046] S100, drop a blood sample on a glass slide and make a blood smear 100. Figure 2 The method for making a blood smear 100 may include the following sub-steps:

[0047] S101. Take two glass slides, one of which is used as a slide to carry the blood film, and the other is used as a pusher to push the blood film on the slide. To ensure the cleanliness of the glass slide, you can clean the glass slide before use. New glass slides often have free alkali, so they can be soaked in cleaning solution or 10% hydrochloric acid for 24 hours, and then thoroughly cleaned. Used glass slides can be put into a proper amount of soapy water or synthetic detergent in clean water and boiled for 20 minutes, then the soap and blood film can be washed off with hot water, and repeatedly rinsed with tap water. If necessary, soak it in 95% ethanol for 1 hour, and then wiped dry or baked for use.

[0048] S102, place the slide glass horizontally, you can hold the slide glass horizontally with your left hand, or you can fix the slide glass on a flat place such as a table, or fix it on a device for pushing blood smear 100. Then, drop a drop of blood sample on one end of the slide glass to form a blood drop. When using the slide glass, you can only hold the edge of the slide glass, and never touch the surface of the slide glass to keep the slide glass clean, dry, neutral, and non-greasy.

[0049] S103, making the push sheet and the glass slide form an angle of 15° to 45°, and making one end of the push sheet slowly approach the blood drop along the first horizontal direction in front of the blood drop.

[0050] S104, when one end of the push sheet contacts the blood drop, so that the blood drop spreads to an appropriate width along the edge of the push sheet, the push sheet is lightly pressed and quickly pushed in a second horizontal direction opposite to the first horizontal direction (i.e., the opposite direction of the first horizontal direction), so that the blood drop is evenly dragged on the glass slide to form a blood film; in this process, the push sheet is always kept at an angle of 15° to 45° with the glass slide. The glass slide with a blood film is a blood film.

[0051] S105. After the blood film on the blood film is dried, the blood film is stained to obtain a blood smear 100. The blood film can be shaken in the air to make the blood film dry quickly. If the blood film is not completely dry and the cells are not firmly attached to the glass slide, they are easy to fall off during the staining process, so the blood film must be fully dried; when the weather is cold or humid, the blood film can be placed in a 37° incubator to keep warm and promote drying to prevent the cells in the blood film from deforming and shrinking. After the blood film is dry, drop Wright's stain on the blood film until the stain submerges the entire blood film and stain for 1 minute. Add an equal amount of distilled water (or buffer) and mix with the stain and stain for another 5 minutes. Finally, rinse off the stain with distilled water, dry with absorbent paper, and dry naturally to obtain an observable blood smear 100.

[0052] A good blood film should be of appropriate thickness, with a clear head, body and tail, evenly distributed, neat edges, and gaps on both sides. It is best to fix and dye the blood film immediately after it is made to avoid cell lysis and degeneration. When dyeing, care should be taken to protect the cells at the tail of the blood film and not to scratch them off. Because larger cells often appear here, the dye should be washed away with running water during rinsing. Do not pour out the dye first to avoid the dye settling on the blood film.

[0053] S200, collecting a microscopic image of the entire blood smear 100 fields of view through a microscope.

[0054] See also Figure 3 In the prior art, the blood smear 100 is generally scanned by a continuous single objective lens field of view, and the clear layer of each objective lens field of view is determined by the hill climbing method. The calculation process of the hill climbing method is as follows:

[0055] After determining the focus elevation (Z direction) range h and estimating the coordinate position of the clear layer, perform layered scanning in the positive Z direction within h with a unit distance of m, determine the clarity of the scanned layer, and compare it with the clarity of the estimated clear layer. When the clarity ratio exceeds p, determine the coordinates (X1, Y1, Z1) of the layer position; immediately perform layered scanning in the negative Z direction of the estimated clear layer with a unit distance of m, determine the clarity of the scanned layer, and compare it with the clarity of the estimated clear layer. When the clarity ratio exceeds p, determine the coordinates (X2, Y2, Z2) of the layer position; at this time, take (|Z1-Z2|) as the elevation, defined as h', within h', take m' as the unit distance, repeat the above method steps, continuously determine and select the clear layer, and finally segment n layers and select the clearest layer in the area as the final image of the position. When using this method for microscopic imaging, characteristic cells are usually selected for positioning, and local cell images are presented. If a clear image of the entire blood smear 100 is to be presented, each area of ​​the blood smear 100 needs to be cut in layers, and then the clear images are spliced ​​and presented. This method requires strong computing power and storage as support, and the image scanning process is time-consuming and inefficient, which limits the imaging speed.

[0056] In this embodiment, the algorithm for identifying clear images is optimized according to the actual situation of the blood smear 100. Figure 4 In this embodiment, the method for acquiring a microscopic image of the entire blood smear 100 field of view may include the following sub-steps:

[0057] S201, establish a spatial rectangular coordinate system with the plane where the blood smear 100 is located as the XOY plane and the elevation direction as the Z axis direction. Generally, a corner point of the blood smear 100 is used as the origin of the spatial rectangular coordinate system, and the length direction and width direction of the blood smear 100 are used as the X axis direction and Y axis direction of the XOY plane, respectively. In this embodiment, the spatial rectangular coordinate system is established with the corner point of the lower left corner of the blood smear 100 as the origin, the length direction of the blood smear 100 as the X direction, the width direction of the blood smear 100 as the Y direction, and the elevation direction as the Z axis direction.

[0058] S202, determine the scanning path 300 of the microscope, based on a single field of view area 200 of the microscope lens (i.e., the area corresponding to one field of view of the microscope lens, corresponding to Figure 3 The blood smear 100 is scanned along the scanning path 300. Figure 5 In this embodiment, when scanning the blood smear 100, a "castle-like" movement method is used to determine the scanning path 300 of the microscope in the X-axis direction and the Y-axis direction. Figure 5 The arrow direction of the scanning path 300 is the moving direction during scanning.

[0059] S203, taking the unit scanning area corresponding to the starting position of the scanning path 300 as the first unit scanning area 201, using a microscope to shoot the first unit scanning area 201 of the scanning path 300, dividing the focus area into n layers along the Z axis direction, and the spacing between adjacent layers is generally 50nm to 500nm, which can be determined according to the actual situation of the specimen in the blood smear 100. The layer image with the highest clarity is identified along the Z axis direction by the hill climbing method as the microscopic image of the first unit scanning area 201, that is, the final image of the first unit scanning area 201; the layer position with the highest clarity found is the focus position with the highest clarity of the microscope. Afterwards, the Z coordinate of the layer image with the highest clarity needs to be calculated, and this is used as the standard layer Z coordinate of the second unit scanning area 202.

[0060] According to the actual situation of the specimen in the blood smear 100, since the imaging distance of the specimen varies only within a very small range, the change in the sharpest focus position of two adjacent unit scanning areas is very small. Therefore, the sharpest focus position of the previous unit scanning area (that is, the Z coordinate of the layer image with the highest clarity) can be directly used as the center to float up and down within a small range to find the layer image with the highest clarity in the next unit scanning area. Its Z coordinate is the sharpest focus position of the unit scanning area, thereby greatly reducing the number of segmented layers.

[0061] In this embodiment, after identifying the layer image with the highest definition in the first unit scanning area 201, the center position coordinates (X a1 , Y a1 , Z a1 ) as the image coordinates of the microscopic image corresponding to the first unit scanning area 201. For example, the center position coordinates of the layer image can be obtained by using a microbubble positioning method. The microbubble positioning method is a commonly used coordinate positioning method and will not be described in detail here. The Z coordinate Z in the center position coordinates a1 That is, the standard layer Z coordinate of the second unit scanning area 202. a1 and Y coordinate Y a1 It is used for positioning the image, so as to locate the position of the microscopic image of the first unit scanning area 201 during subsequent image stitching.

[0062] S204, using a microscope to photograph the next unit scanning area of ​​the scanning path 300, and taking the standard layer Z coordinate of the unit scanning area as a reference, dividing 2m+1 layers along the Z axis direction, 2m+1<n. Wherein, taking the standard layer Z coordinate as a reference, the method of dividing the focus area of ​​the recognition image into 2m+1 layers along the Z axis direction is:

[0063] The Z coordinate of the standard layer is used as the standard layer. Starting from the standard layer, the predetermined step value is stepped upward and sequentially divided to form m layers. Starting from the standard layer, the predetermined step value is stepped downward and sequentially divided to form m layers, and 2m+1 layers including the standard layer are obtained. The step value generally ranges from 50nm to 500nm, which can be determined according to the actual situation of the specimen in the blood smear 100. In combination with the implementation situation, in order to simplify the calculation, the value of m is generally 2 or 3 to find a clear image.

[0064] In this embodiment, m=2. For example, after obtaining the microscopic image of the first unit scanning area 201, the second unit scanning area 202 is photographed. At this time, according to the coordinate Y a1 The standard layer of the second unit scanning area 202 is determined, and the layer image of the standard layer is first obtained as the first layer image. Then, based on the standard layer, a layer image can be obtained by moving up by one step value from the standard layer as the second layer image, and then by moving up by one step value as the third layer image, and then a layer image can be obtained by moving down by one step value from the standard layer as the fourth layer image, and then by moving down by one step value as the fifth layer image, thereby obtaining five layer images. Of course, depending on the implementation, m=3 can sometimes be taken, so that three layers are divided above and below the standard layer, thereby obtaining seven layer images.

[0065] S205, identify the layer image with the highest definition from the 2m+1 layer images as the microscopic image of the unit scanning area, and calculate the Z-axis coordinate of the layer image with the highest definition as the standard layer Z coordinate of the next unit scanning area. In this embodiment, a convolutional neural network model is used to identify the layer image with the highest definition, and the specific method is as follows:

[0066] A convolutional neural network model for predicting the clarity of an image is pre-set, and the edge, shape, and texture features of the cell microscopic image are annotated. The annotated cell microscopic image is used to train the convolutional neural network model to obtain a clarity recognition model that can judge the clarity of a new unknown image. During recognition, each layer image is input into the clarity recognition model to obtain the clarity prediction value of each layer image, and the layer image with the highest clarity prediction value is output as the layer image with the highest clarity.

[0067] In order to test the accuracy of the clarity recognition model, the clarity factor calculation formula is also used in this step to perform dual recognition and judgment on the image clarity. The clarity factor calculation formula can be used to calculate the clarity factor of each layer image according to the grayscale of the image, and then determine whether the layer image output by the clarity recognition model is consistent with the layer image with the largest clarity factor value. If they are consistent, it can be considered that the layer image output by the clarity recognition model is the image with the highest clarity, that is, the clarity recognition model output is accurate. If the layer image output by the clarity recognition model is inconsistent with the layer image with the largest clarity factor value, it is considered that the layer image output by the clarity recognition model may not be the image with the highest clarity. The layer image output by the clarity recognition model is marked and can be manually verified later. If it is confirmed that the layer image output by the clarity recognition model is not the image with the highest clarity, the clarity recognition model can be improved. The clarity factor calculation formula is as follows:

[0068]

[0069] Where σ represents the clarity factor; N represents the number of all pixels in the area; x i represents the gray level of the i-th pixel; μ represents the average gray level of the image.

[0070] Since the prediction method using the convolutional neural network model is more accurate, the layer image output by the convolutional neural network model is always used as the microscopic image of the unit scanning area. The calculation formula of the clarity factor is only used to assist in verifying the output of the convolutional neural network model and will not be used as the main basis for judgment.

[0071] For example, for the five layer images of the second unit scanning area 202, the five layer images are first input into the clarity recognition model during recognition, and the clarity recognition model outputs a layer image as the microscopic image of the second unit scanning area 202; thereafter, the clarity factors of the five layer images are calculated respectively through the formula, and the layer image with the largest clarity factor is compared with the layer image output by the clarity recognition model to see whether they are consistent, so as to further determine whether the output of the clarity recognition model is accurate.

[0072] Of course, in this step, the center position coordinates (X a2 , Y a2 , Z a2 ) as the image coordinates of the microscopic image corresponding to the second unit scanning area 202. The Z coordinate Z in the center position coordinates a2 This is the standard layer Z coordinate of the third unit scanning area. a2 and Y coordinate Y a2 It is used for positioning the image, so as to locate the position of the microscopic image of the second unit scanning area 202 during subsequent image stitching.

[0073] S206, repeating steps S204 and S205 to obtain microscopic images of each region of the blood smear 100, and stitching together to obtain a microscopic image of the entire field of view of the blood smear 100. For example, for the third unit scanning area, according to the coordinate Z a2 Determine the standard layer of the third unit scanning area, and obtain the 5 layer images of the third unit scanning area by stepping up and down the standard layer, and then obtain the microscopic image of the third unit scanning area and the center position coordinates (X a3 , Y a3 , Z a3 ), Z coordinate Z a3 This is the standard layer Z coordinate of the fourth unit scanning area. a2 and Y coordinate Y a2 It is used for image positioning, so as to locate the position of the microscopic image of the third unit scanning area during subsequent image stitching.

[0074] After that, the above operation is repeated for each subsequent unit scanning area in sequence until the scanning of the entire blood smear 100 is completed, and the microscopic images of all the unit scanning areas of the blood smear 100 are obtained. Finally, the positions of the microscopic images are arranged according to the X coordinates and Y coordinates in the image coordinates of each microscopic image, and spliced ​​to obtain a clear microscopic image of the entire field of view of the blood smear 100.

[0075] S300, processing the microscopic image to obtain cell microscopic image features. For example, by processing the microscopic image, features such as cell edge shape, cell diameter, cell color, cell nucleus distribution, cell structure, etc. can be obtained, and a cell database can be established using the YOLO v5 algorithm.

[0076] After obtaining the cell microscopic image features, experts can also input the morphological features of peripheral blood-related disease cells, and automatically determine whether the cells in the acquired microscopic images are abnormal by comparing the features with the cells in the microscopic images in the database, and automatically identify the cause of the abnormality when there is an abnormality. At the same time, the above method can also be used to provide auxiliary diagnosis functions, condense the wisdom of experts, realize informatization, and perform auxiliary diagnosis based on the cell features of clear images to improve the accuracy of diagnosis.

[0077] In this embodiment, blood cell detection is facilitated by making a blood smear 100, and the method of collecting microscopic images of blood smears 100 by microscope is improved. When collecting microscopic images of blood smears 100, only the first unit scanning area 201 needs to use the hill climbing method to identify the clearest image. Starting from the second unit scanning area 202, the processing of subsequent unit scanning areas no longer divides the layers of each area into n layers and then identifies and screens the clearest image, but only divides them into 5 layers, and identifies and screens the clearest image in the 5 layers. Compared with the existing method, when this embodiment processes clear images of the same number of fields of view, the number of required segmentations and the number of identifications after segmentation are reduced, and the processing volume is reduced by about n / 5 times of the existing method, the requirement for computing power is greatly reduced, and the imaging speed is improved. Scanning and processing blood smears using the above method can truly restore various cell characteristics, perfectly present the delicate texture, color and internal details of the cells, including the clear reproduction of cell lines, cytoplasm, particles, etc., simulate manual focusing, accurately restore cell pathological characteristics, and provide a judgment basis for early screening of blood diseases and infectious diseases.

[0078] The above embodiments only express the preferred implementation modes of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for those of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A blood cell detection method based on microscopic image processing, characterized in that: The following steps are involved: S100, dropping a blood sample on a glass slide and making a blood smear; S200, collecting a microscopic image of the entire blood smear field of view through a microscope; S300, processing the microscopic image to obtain cell microscopic image features.

2. The blood cell detection method based on microscopic image processing according to claim 1, characterized in that: The step S100 includes the following sub-steps: S101, take two glass slides, one of which is used as a slide glass and the other is used as a push slide; S102, placing the glass slide horizontally, and dropping a drop of blood sample on one end of the glass slide to form a blood drop; S103, making the pusher slide and the glass slide form an angle of 15° to 45° in front of the blood drop and slowly approaching the blood drop; S104, when one end of the push sheet contacts the blood drop, so that the blood drop spreads to a proper width along the edge of the push sheet, the push sheet is lightly pressed and quickly pushed in the opposite direction, so that the blood drop is evenly dragged on the slide to form a blood film; S105, after the blood film is dried, staining the blood film to obtain a blood smear.

3. The blood cell detection method based on microscopic image processing according to claim 1, characterized in that: The step S200 includes the following sub-steps: S201, establishing a spatial rectangular coordinate system with the blood smear plane as the XOY plane and the elevation direction as the Z axis direction; S202, determining a scanning path of the microscope, taking a single field of view of the microscope as a unit of scanning area, and scanning the blood smear along the scanning path; S203, photographing the first unit scanning area of ​​the scanning path with a microscope, dividing the focus area of ​​the microscope into n layers along the Z-axis direction, identifying the layer image with the highest definition along the Z-axis direction as the microscopic image of the first unit scanning area by a hill climbing method, and calculating the Z-axis coordinate of the layer image as the standard layer Z coordinate of the second unit scanning area; S204, photographing the next unit scanning area of ​​the scanning path using a microscope, and dividing 2m+1 layers along the Z axis direction based on the standard layer Z coordinate of the unit scanning area, 2m+1<n; S205, identifying the layer image with the highest definition from the 2m+1 layer images as the microscopic image of the unit scanning area, and calculating the Z-axis coordinate of the layer image as the standard layer Z coordinate of the next unit scanning area; S206. Repeat steps S204 and S205 to obtain microscopic images of each unit scanning area of ​​the blood smear, and stitch them together to obtain a microscopic image of the entire blood smear field of view.

4. The blood cell detection method based on microscopic image processing according to claim 3, characterized in that: In the step S201, a corner point of the blood smear is taken as the origin of the spatial rectangular coordinate system, and the length direction and width direction of the blood smear are taken as the X-axis direction and Y-axis direction of the XOY plane respectively; in the step S202, when scanning the blood smear, a "battlement-like" movement method is used in the X-axis direction and the Y-axis direction to determine the scanning path of the microscope.

5. The blood cell detection method based on microscopic image processing according to claim 3, characterized in that: In the step S204, the method of dividing the focus area of ​​the recognition image into 2m+1 layers along the Z axis direction based on the standard layer Z coordinate is: Take the Z coordinate of the standard layer as the standard layer, start from the standard layer and step upward with a predetermined step value and divide it in sequence to form m layers, start from the standard layer and step downward with a predetermined step value and divide it in sequence to form m layers, and obtain 2m+1 layers including the standard layer.

6. The blood cell detection method based on microscopic image processing according to claim 3, characterized in that: The value of m is 2 or 3; the predetermined step value is 50nm to 500nm.

7. The blood cell detection method based on microscopic image processing according to claim 2, characterized in that: In the step S203 and the step S205, after identifying the layer image with the highest definition, the microbubble positioning method is used to obtain the center position coordinates of the layer image as the image coordinates, and the Z coordinate in the center position coordinates is the standard layer Z coordinate of the next unit scanning area; in the step S206, the positions of each microscopic image are arranged according to the X coordinate and Y coordinate in the image coordinates, and splicing is performed.

8. The blood cell detection method based on microscopic image processing according to any one of claims 1 to 7, characterized in that: In the step S205, the method for identifying the layer image with the highest definition is: Presetting a convolutional neural network model for predicting the clarity of an image, and training the convolutional neural network model to obtain a clarity recognition model; Each layer image is input into the clarity recognition model to obtain the clarity prediction value of each layer image, and the layer image with the highest clarity prediction value is output as the layer image with the highest clarity.

9. The blood cell detection method based on microscopic image processing according to claim 8, characterized in that: In the step S205, a definition factor calculation formula is also used to calculate the definition factor of each layer image. The definition factor calculation formula is as follows: Where σ represents the clarity factor; N represents the number of all pixels in the area; x i represents the gray level of the i-th pixel; μ represents the average gray level of the image; After calculating the clarity factor of each layer image, it is determined whether the layer image output by the clarity recognition model is consistent with the layer image with the largest clarity factor value. If they are inconsistent, the layer image output by the clarity recognition model is marked.

10. The blood cell detection method based on microscopic image processing according to claim 1, characterized in that: In the step S300, the acquired cell microscopic image features include cell edge shape, cell diameter, cell color, cell nucleus distribution and cell structure.

Images