WO2022041210A1 - 定位血涂片上血膜的感兴趣区域的方法和细胞图像分析仪 - Google Patents

定位血涂片上血膜的感兴趣区域的方法和细胞图像分析仪 Download PDF

Info

Publication number
WO2022041210A1
WO2022041210A1 PCT/CN2020/112526 CN2020112526W WO2022041210A1 WO 2022041210 A1 WO2022041210 A1 WO 2022041210A1 CN 2020112526 W CN2020112526 W CN 2020112526W WO 2022041210 A1 WO2022041210 A1 WO 2022041210A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
cell
target
blood
control device
Prior art date
Application number
PCT/CN2020/112526
Other languages
English (en)
French (fr)
Inventor
罗玮
邢圆
叶波
祁欢
余珊
陈巧妮
叶燚
Original Assignee
深圳迈瑞生物医疗电子股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳迈瑞生物医疗电子股份有限公司 filed Critical 深圳迈瑞生物医疗电子股份有限公司
Priority to PCT/CN2020/112526 priority Critical patent/WO2022041210A1/zh
Priority to CN202080104241.4A priority patent/CN116097083A/zh
Publication of WO2022041210A1 publication Critical patent/WO2022041210A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N15/00Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
    • G01N15/10Investigating individual particles
    • G01N15/14Optical investigation techniques, e.g. flow cytometry

Definitions

  • the invention relates to the field of medical detection, in particular to a method for locating a region of interest of a blood film on a blood smear and a cell image analyzer.
  • the automatic blood cell digital image analysis system can automatically load and unload blood smears, complete the functions of cell positioning and shooting, cell identification and pre-classification, and its detection speed and cell image quality are greatly improved. To a certain extent, it can replace the work of manual microscopy.
  • the existing blood cell digital image analysis system automatically scans the blood smear, all of which scan the body-tail junction of the blood film, which is suitable for observing red blood cells and white blood cells. However, platelet aggregation, large abnormal cells, etc. may appear in other parts of the blood smear, and only scanning the junction of the body and tail has the risk of missed detection.
  • the present application provides a method and a cell image analyzer for locating a region of interest of a blood film on a blood smear, which is convenient for users to locate the region of interest faster and more accurately It is convenient to increase the scanning area of the region of interest according to user needs.
  • the application provides a method of locating a region of interest of a blood film on a blood smear, the method comprising:
  • the control device acquires an initial photographing position and a final photographing position where the image photographing device performs cell photographing on the blood smear, wherein a line connecting the initial photographing position and the final photographing position passes through the region of interest;
  • the control device causes the image capturing device to move relative to the blood smear, and enables the image capturing device to capture a plurality of cell images at different positions of the blood smear from the initial capturing point, Stop the relative movement and shooting until the final shooting position;
  • the control device determines the target position of the region of interest according to the image features and shooting positions of the plurality of cell images.
  • a method for locating a region of interest of a blood film on a blood smear comprising:
  • the control device acquires the starting shooting position and the preset moving direction of the cell shooting of the blood smear by the image shooting device;
  • the control device causes the image capture device to move relative to the blood smear, so that the image capture device starts from the initial capture point and captures the cell image of the blood smear along the preset moving direction and analyzing the cell image;
  • the control device determines that the change of the image feature of the current cell image relative to the image feature of the cell image captured before or after the current cell image satisfies the third preset condition, then the current cell image capture position Determine the target location for the region of interest.
  • a method for locating a region of interest of a blood film on a blood smear comprising:
  • control device receives the mode selection command
  • the mode selection instruction received by the control device is the dynamic mode, determine the target position of the region of interest according to the above method;
  • the mode selection instruction received by the control device is a fixed mode, acquiring a fixed preset target position of the region of interest;
  • the control device controls the relative movement of the image capturing device and the blood smear according to the target position of the region of interest, so as to locate the target position of the region of interest.
  • a cell image analyzer comprising:
  • An image capturing device having a camera and a lens group, for capturing images of cells in the blood film on the blood smear;
  • a smear moving device used to relatively move the image capturing device and the blood smear
  • control device in communication with the image capturing device and the smear moving device and configured to:
  • the target position of the region of interest is determined according to the image features and shooting positions of the plurality of cell images.
  • a fifth aspect provides a cell image analyzer, comprising:
  • An image capturing device having a camera and a lens group, for capturing images of cells in the blood film on the blood smear;
  • a smear moving device used to relatively move the image capturing device and the blood smear
  • control device in communication with the image capturing device and the smear moving device and configured to:
  • the shooting position of the current cell image is determined as the region of interest. target location.
  • a sixth aspect provides a cell image analyzer, comprising:
  • An image capturing device having a camera and a lens group, for capturing images of cells in the blood film on the blood smear;
  • a smear moving device used to relatively move the image capturing device and the blood smear
  • a mode selection device for selecting a dynamic mode or a fixed mode, in which the target position of the region of interest can be dynamically confirmed according to different blood smears, and in the fixed mode, the target position of the region of interest can be fixedly preset the target location of the area;
  • control device in communication with the image capturing device, the smear moving device and the mode selection device and configured to:
  • the smear moving device is controlled so that the image capturing device and the blood smear move relative to each other, so as to locate the target position of the region of interest.
  • a plurality of cell images are first captured from the initial capture position, and then the target position of the region of interest is determined by the features of the plurality of cell images and the capture position.
  • the target position may be the blood membrane boundary, such as the blood membrane two.
  • FIG. 1 is a flowchart of a method for locating a region of interest according to an embodiment of the present invention
  • FIG. 2 is a schematic diagram of a blood film according to an embodiment of the present invention.
  • 3 to 5 are schematic diagrams of cell images according to embodiments of the present invention.
  • FIG. 6 is a schematic diagram of an edge shooting path according to an embodiment of the present invention.
  • FIG. 7 and 8 are schematic diagrams of the blood film tail according to an embodiment of the present invention.
  • FIG. 9 is a schematic diagram of a tail shooting path according to an embodiment of the present invention.
  • FIG. 10 is a schematic diagram of a shooting path according to an embodiment of the present invention.
  • FIG. 11 and FIG. 12 are schematic structural diagrams of a cell image analyzer according to an embodiment of the present invention.
  • FIG. 13 is a schematic structural diagram of a control device according to an embodiment of the present invention.
  • Figures 14 to 16 and 19 to 20 are schematic diagrams of confirming regions of interest according to embodiments of the present invention.
  • Figures 17 to 18 and Figures 21 to 22 are flowcharts of a method for confirming that a region of interest is determined according to an embodiment of the present invention
  • FIG. 23 is a schematic diagram of a sample analysis system according to an embodiment of the present invention.
  • Figure 24 and Figure 25 are schematic structural diagrams of the smear preparation device according to the embodiment of the present invention.
  • FIG. 26 and FIG. 27 are schematic diagrams showing the structure of the cell image analyzer according to the embodiment of the present invention.
  • the embodiment of the present invention provides a method for locating a region of interest, using a cell image analyzer.
  • at least one cell image at different shooting positions of the blood smear is acquired by an image acquisition device, and by analyzing whether the at least one cell image satisfies a preset condition (for example, comparing the features in the image with a preset threshold), It is judged whether the region of interest is found, and the position of the region of interest on the blood smear is determined, so that the region of interest can be accurately photographed subsequently.
  • a preset condition for example, comparing the features in the image with a preset threshold
  • the embodiments of the present invention can dynamically determine the position of the region of interest for each blood smear to be tested, especially the position of the blood film boundary on the blood smear, so that the image acquisition device can accurately detect the blood The area near the membrane boundary was photographed.
  • FIG. 1 is a flowchart of a method for locating a region of interest of a blood film on a blood smear according to an embodiment of the present invention, and the method includes:
  • Step 101 the control device acquires the initial shooting position and the final shooting position where the image shooting device performs cell shooting on the blood smear, wherein the connecting line between the initial shooting position and the final shooting position passes through the region of interest;
  • Step 102 the control device makes the image capturing device and the blood smear move relative to each other, and makes the image capturing device start to capture a plurality of different positions of the blood smear from the starting shooting point. cell images, until the final photographing position stops the relative movement and photographing;
  • Step 103 the control device determines the target position of the region of interest according to the image features and shooting positions of the plurality of cell images.
  • the blood smear has a blood film
  • the blood smear is formed by, for example, coating a blood sample on a blank glass slide
  • the blood film is a thin film formed by the blood coated on the blood smear.
  • the blood smear is usually rectangular, and the blood film is smeared from the A1 end to the B1 end on the blood smear.
  • the blood film may include a head, a body, and a tail along the smearing direction, that is, from A1 to B1 as shown in FIG. 2 , which are respectively shown in dotted boxes.
  • the region of interest may be the edge of the blood film, or may be the tail of the blood film, or may be the edge of the blood film and the tail of the blood film.
  • a plurality of cell images are first captured from the initial shooting position and the final shooting position, and then the target position of the region of interest is determined according to the characteristics of the multiple cell images and the shooting position, and the target position can be the edge or the tail.
  • the target position can be the edge or the tail.
  • the image capturing device may capture images under different objective lenses, for example, capturing cell images under an objective lens of not less than 40X (40 times), preferably at 100X (100 times) Acquire images of cells under the objective lens.
  • the control device causes the image capture device to capture a plurality of cell images at different positions of the blood smear from the starting capture point, including:
  • the control device enables the image capture device to continuously capture a plurality of cell images at different positions of the blood smear at preset image intervals from the start capture point.
  • the preset image interval may be a time interval or a distance interval.
  • the preferred solution may be equal intervals.
  • the two frames of cell images before and after can be taken consecutively.
  • the distance interval at this time can be the width of the field of view or the length of the field of view of the imaging device; or, it can be taken at intervals with a certain interval.
  • step 103 the control device determines the target position of the region of interest according to the image features and shooting positions of the multiple cell images, including:
  • the control device sequentially analyzes the image features of at least two cell images taken successively, especially successively taken successively, in the plurality of cell images;
  • the shooting position of one cell image in the at least two cell images is the sensory image.
  • the image feature includes a cell region, and the change of the image feature of the at least two cell images captured successively satisfies the first preset condition, then one of the at least two cell images
  • the shooting position of the cell image is the target position of the region of interest, including:
  • the control device identifies the cell area in the analyzed cell image according to the grayscale or color difference between the cell and the background in the analyzed cell image;
  • the capturing position of the first captured or last captured cell image in the at least two cell images is the position of interest.
  • which frame of cell image is the target position of the region of interest is usually determined by the change of image features, such as the change of the area of the cell region, of at least two cell images captured successively, especially successively captured cell images.
  • the region of interest includes the long edge of the blood film
  • the capturing position of one cell image in the at least two cell images is the target position of the region of interest, including:
  • the image feature of the first or last cell image of the at least two successively captured cell images indicates that the first or last cell image corresponds to the blank part of the cell area (as shown in Figure 4 ) ), and the image features of at least one remaining cell image indicate that the remaining cell image corresponds to a full blank area (as shown in Figure 3) or a full cell area (as shown in Figure 5), then the first or last photographed image
  • the shooting position of the cell image is the target position of the long edge.
  • the above method in this embodiment acquires the region of interest according to the change of the image features. If the partial blank cell area changes to the full blank area or the full cell area, or from the complete blank area or the whole cell area to the partial blank partial cell area, the partial blank cell area is the target position of the long edge.
  • control device analyzes the image features of the cell image, including:
  • the control device identifies the cell area in the analyzed cell image according to the grayscale or color difference between the cell and the background in the cell image;
  • the cell image corresponds to a full blank area
  • the cell image corresponds to a part of the blank cell region
  • the cell image corresponds to the whole cell region
  • the cell image corresponds to a part of the blank part of the cell area.
  • the first threshold may be set to 0.01*total area of the field of view (the entire image), that is, if the area of the cell area of the cell image is less than 1% of the total area of the field of view, it is considered that the cell image corresponds to a full blank area; If the area of the cell area is greater than or equal to 1% of the total area of the field of view, the cell image is considered to correspond to a part of the blank part of the cell area.
  • the second threshold can be set to 0.70*total area of the field of view, that is, if the area of the cell area is greater than 70% of the total area of the field of view, the cell image is considered to correspond to the whole cell area; if the cell area is less than or equal to 0.70*total area of the field of view, the cell The image corresponds to a partially blank cell area. It can be understood that, in actual use, since the position of the blood film is within the controllable range, the initial shooting point and shooting direction can be roughly determined, and the above-mentioned first threshold and second threshold can be used alone to determine the blank part of the cell area.
  • the condition of the whole blank area or the whole cell area for example, when shooting from the middle of the blood membrane to the outside of the long edge, it is only necessary to judge the change from the whole cell area to the partially blank part of the cell area, that is, you can only use the
  • the second threshold is used for judgment; similarly, in the case of shooting from the outside of the long edge to the middle of the blood film, only the first threshold may be used for judgment.
  • the first threshold and the second threshold can also be used together as conditions for judging the above-mentioned different regions.
  • the cell image corresponds to a part of the blank part of the cell area.
  • the cell area ratio of the first cell image is greater than 70% (that is, in the whole cell area), and the cell area ratio of the last cell image starts to be less than 1. % (i.e. into a completely blank area), then the position of the cell image taken before or after the last cell image is the long edge edge.
  • the first threshold and/or the second threshold can also be expressed as the first area ratio threshold, for example, the first threshold can be the total area of the cell area and the field of view.
  • the area to area ratio is 1%.
  • the area can also be the number of pixels, that is, the area and the pixels can be converted.
  • the number can also be converted to each other.
  • the number of pixels in the entire image is 5,000,000, and the threshold calculated according to the percentage of 1% is the number of pixels 50,000.
  • the cell image shown in Figure 3 is an image of a full blank area
  • Figure 4 is an image of a partially blank cell area
  • Figure 5 is an image of a full cell area.
  • the cell area is first identified by the grayscale or color difference between the cells and the background, and then the image features of the cell image can be analyzed by setting the first threshold and/or the second threshold, that is, the cell image can be analyzed.
  • the full blank area the partial blank partial cell area or the whole cell area.
  • control device may determine the target location of the region of interest by analyzing image features of a single cell image among the plurality of cell images.
  • the shooting position of any cell image is that the region of interest includes all cells in the region of interest. the long edge of the blood film. For example, by analyzing the image features of a certain cell image by the aforementioned method, and determining the blank cell area corresponding to the cell image, it can be determined that the position of the cell image captured by the cell image is the long edge.
  • the long edge edge can be determined by analyzing any one of the multiple cell images obtained by shooting, such as analyzing the multiple cell images sequentially or in other sequences.
  • the control device analyzes the image feature of any cell image in the plurality of cell images, and obtains the distribution information of the cell region of the any cell image; if the distribution information satisfies a preset distribution condition, determine the The capture position of any cell image is the target position of the long edge.
  • the cell area Since in the cell image captured at the target position on the long edge, the cell area will show a distribution from the whole cell area to the partially blank part cell area, or from the partially blank part cell area to the complete blank area, or from the whole cell area
  • the control device may obtain at least two secondary cell images by segmenting any cell image in the plurality of cell images, and analyze the image features of the two secondary cell images;
  • the image features of the two secondary cell images respectively indicate that one of the two secondary cell images corresponds to a full blank area, the other corresponds to a partially blank cell area or a full cell area; or, if the two secondary cell images
  • the image features of the two secondary cell images respectively indicate that one of the two secondary cell images corresponds to the whole cell area, the other one corresponds to the partial blank cell area or the complete blank area; then it is determined that the shooting position of any cell image is the edge of the long edge target location.
  • At least one dividing line may be preset in any cell image among the plurality of cell images to obtain at least two cell images secondary to the any cell image.
  • the dividing line is preferably a straight line parallel to the edge direction of the blood smear; the dividing line can be set in the middle of any cell image.
  • the first threshold is 1% of the total area of the secondary cell image
  • the predetermined threshold is 50% of the total area of the secondary cell image (of course, the predetermined threshold may also be The same as the first threshold or the second threshold), it can be considered that the secondary cell image corresponds to a partial blank partial cell area or a whole cell area.
  • the image features of the two secondary cell images respectively indicate that one of the two secondary cell images corresponds to a full blank area, the other corresponds to a partial blank cell area or a full cell area, then determine the The capture position of any cell image is the target position of the long edge.
  • the first threshold and/or the second threshold can also be used to determine that the secondary cell image corresponds to a full blank area, a partial blank partial cell area, or a full cell area, respectively. Therefore, if the image features of the two secondary cell images respectively indicate that one of the two secondary cell images corresponds to a whole cell area, the other one corresponds to a partial blank cell area or a complete blank area; The shooting position of a cell image is the target position of the long edge. Similar to the foregoing embodiments, the first threshold and the second threshold may be fixed values, or may be determined by a preset ratio of the cell area to the total area of the secondary cell image.
  • the distance between the two cell images taken before and after the image is smaller than the imaging distance.
  • the distance interval may match the position of the dividing line, a first threshold, a second threshold or a predetermined threshold.
  • the distance between two consecutive images may preferably be set as 50% of the width of the field of view of the cell image.
  • the initial photographing position and the final photographing position are respectively located on both sides of one long edge of the blood film, or the initial photographing position and the final photographing position are respectively located on the Beyond the long edge of the blood film on both sides.
  • the blood film includes a head, a body and a tail along the smearing direction on the blood smear, and the long edge is the long edge of the head or the body.
  • the starting and final shooting positions may be located on both sides of one long edge of the blood film as indicated by D1 and E1, or may be located on the other side of the blood film as indicated by H1 and F1.
  • the two sides of one long edge, or as shown in D1 and F1, are respectively located outside the two long edges of the blood film.
  • the initial shooting position and the final shooting position may be located outside the long edges on both sides of the blood film body as shown in G1 and F1, or may be as shown in D1 and I1 Beyond the edges of the long sides of the blood film head.
  • D1, F1, G1, and I1 can be any positions between the long edge of the blood film and the long edge of the blood smear as indicated by C1, and E1 and H1 can be blood smears. anywhere within the membrane.
  • the above-mentioned starting shooting position and final shooting position may also be interchanged.
  • the region of interest is the long edge of the blood film, such as the upper edge of the blood film shown in FIG. 2 .
  • the initial shooting position and the final shooting position are E1 and D1 respectively, that is, the control device makes the image shooting device continuously shoot multiple cell images at different positions of the blood smear at preset image intervals from point E1 until point D1. Then, the control device analyzes the image features of at least two consecutively photographed cell images among the plurality of consecutively photographed cell images.
  • the shooting position of the first cell image is the target position of the long edge; or, if the last cell image captured in the at least two consecutive cell images is a partial cell image If there is a blank part of the cell area (as shown in Figure 4), and at least one other cell image is a whole cell area (as shown in Figure 5), the shooting position of the last captured cell image is the target of the long edge Location. It can also be said that, as shown in FIG.
  • the edges can be found from the blank positions on both sides to the middle, and multiple images 1400 can be taken along the direction perpendicular to the long edge of the blood smear (as shown by the arrow in the figure).
  • the blank area then the edge area with blanks and cells, and then fully into the cell area.
  • the location of the image 1401 in FIG. 14 is an actual location where the long edge is located.
  • the edge can also be found from the middle position to the blank positions on both sides, as shown in Figure 15, and a series of images are taken along the direction perpendicular to the long edge of the blood smear (as shown by the arrow direction in Figure 15). 1500, first the complete cell area, then the edge area with blanks and cells, and then completely into the blank area; the shooting starting point is determined according to the starting shooting position, the image position (several number) of the edge area, and the distance between adjacent images The actual distance to the edge location to determine the actual location of the long edge edge. In Fig. 15, the image 1501 is an actual position where the long edge is located.
  • the regions of interest are the two long edges of the blood film, such as the upper and lower edges of the blood film shown in FIG. 2 .
  • the initial shooting position and the final shooting position are F1 and G1 respectively, that is, the control device makes the image shooting device continuously shoot multiple cell images at different positions of the blood smear at preset image intervals from point F1 until point G1. Then, the control device analyzes the image features of at least two consecutively photographed cell images among the plurality of consecutively photographed cell images. If the at least two consecutive cell images are changed from a partially blank part of the cell area (as shown in FIG. 4 ) to a completely blank area (as shown in FIG. 3 ), or from a full cell area (as shown in FIG.
  • the photographing position of the cell image with the partially blank partial cell area is the target position of the long edge of the blood membrane. That is, a series of images 1600 can be taken directly from one blank position to the other blank position, as shown in Figure 16, along the direction perpendicular to the long edge of the blood smear (as shown by the arrow in Figure 16). , and then locate the edge positions on both sides. According to the image position (number of images) of the edge area and the distance between adjacent images, the actual distance from the shooting start point to the edge position is determined, and then the actual position of the edge is determined. In Fig. 16, the image 1601 is an actual position where the long edge is located.
  • the method further includes:
  • Step 1710 the control device determines a first target shooting position according to the target position of the long edge
  • Step 1720 the control device causes the image capturing device to move relative to the blood smear, so as to position the image capturing device to the first target shooting position;
  • Step 1730 the control device causes the image capture device and the blood smear to continue to move relative to the first target capture position along the edge capture path toward the tail, so that the image capture device captures the image.
  • the edge photographing path toward the tail may be a path parallel to the edge of the blood smear, or a path parallel to the smearing direction.
  • the shooting can be performed at time intervals or distance intervals as in the above-mentioned embodiments.
  • whether the blood smear is abnormal can also be determined according to the target image
  • the method further includes outputting, by the control device, a plurality of first target cell images of the long edge of the blood film, for example, outputting to a display device , so that the user can judge whether there are abnormal white blood cells, abnormal platelet aggregation, etc. in the blood smear according to the first target cell image.
  • control device can also automatically determine whether there is an abnormality in the blood smear according to the target image, that is, the method further includes:
  • the control device determines whether there is abnormal white blood cell and/or platelet aggregation in the blood smear according to a plurality of first target cell images on the long edge of the blood film.
  • the method further includes:
  • Step 1810 the control device determines the second target shooting position of the long edge according to the target position of the long edge, wherein the second target shooting position is different from the first target shooting position;
  • Step 1820 the control device causes the image capturing device to move relative to the blood smear, so as to position the image capturing device to the second target shooting position;
  • Step 1830 the control device causes the image capture device and the blood smear to continue to move relative to the edge capture path starting from the second target capture position, so that the image capture device captures the Multiple second target cell images of the long edge of the blood membrane.
  • the second target shooting position is farther away from the long edge of the blood smear than the first target shooting position in a direction perpendicular to the long edge of the blood smear (or perpendicular to the smearing direction).
  • the line connecting the first target shooting position and the second target shooting position may be perpendicular to the smearing direction (the direction of the long edge of the blood smear), or may not be perpendicular.
  • the method further includes:
  • the control device makes the image capturing device and the blood smear start from the third target shooting position and shoot the edge according to the third target shooting position of the long edge.
  • the paths continue to move relative to each other in parallel, so that the image capturing device captures a plurality of third target cell images of the long edge of the blood film, wherein the third target capturing position is different from the second target capturing position .
  • FIG. 6 is a schematic diagram of an edge shooting path according to an embodiment of the present invention.
  • the first target shooting position may be point A2, and the edge shooting path may be a path from A2 to B2.
  • the second target shooting position may be point C2, and the corresponding edge shooting path may be C2-D2.
  • the second target shooting position may be point D2, and the corresponding edge shooting path may be D2-C2.
  • the above-mentioned edge shooting paths may be repeated many times, until the area of the captured cell image reaches the preset area, or the total number of shooting paths that are scheduled to be captured, and then the shoot.
  • the purpose of this is to obtain more information on edge cells to more accurately judge abnormalities, such as platelet aggregation.
  • the user can locate the region of interest faster and more accurately, and it is convenient to increase the scanning area of the region of interest according to the user's needs.
  • whether the blood smear is abnormal can also be determined according to the target image
  • the method further includes outputting, by the control device, a plurality of first target cell images and a plurality of second target cell images of the long edge of the blood film
  • the image and the optional third target cell image are output to the display device, so that the user can judge whether there are abnormal white blood cells in the blood smear according to the first target cell image, the second target cell image and the optional third target cell image , abnormal platelet aggregation, etc.
  • whether the blood smear is abnormal can also be automatically determined by the control device according to the target image, that is, the method further includes: the control device according to a plurality of first targets on the long edge of the blood film. Whether the blood smear has abnormal leukocyte and/or platelet aggregation is determined from the cell image and the plurality of second target images and optionally the plurality of third target images.
  • the region of interest further includes the tail of the blood film
  • the tail of the blood film can be identified while the long edge of the blood film is photographed, more precisely, the tail edge is searched
  • the method also further include:
  • the control device sequentially analyzes the image features of at least two first target cell images taken successively in the plurality of first target cell images;
  • the at least two first target cell images taken successively indicate that red blood cells are aggregated into clusters and/or the tail features or tail edge features of small cell areas appear, then the at least two first target cells
  • the shooting position of the last image of the first target cell in the image is the target position of the tail.
  • the change of the image features of the at least two first target cell images taken successively indicates that red blood cells aggregate into clusters and/or tail features with small cell areas, including:
  • the erythrocyte aggregation group numerical feature of the last captured first target cell image is greater than the third threshold and/or the cell area area is smaller than the fourth threshold, and the remaining at least one first target cell image is The erythrocyte aggregation group numerical feature of the target cell image is less than or equal to the third threshold and/or the area of the cell region is greater than or equal to the fourth threshold.
  • the erythrocyte aggregate numerical feature can be the ratio of erythrocyte aggregates, or it can be the number of erythrocyte aggregates, or it can be the size of the area.
  • the third threshold may be 0.5*cell area
  • the fourth threshold may be 0.25*total area of the visual field (the area of the entire image), that is, in the cell image, the area of the cell area is smaller than the total area of the visual field 25%, and/or the ratio of the area of aggregated cells to the area of the cell area exceeds the threshold of 50%, it is considered that the tail edge has been reached.
  • the way to judge the clustering here is that the size of the connected domain of the cell block exceeds a certain threshold, such as 200 square microns.
  • the third threshold value and the fourth threshold value can also be converted into the third area ratio threshold value and the fourth area ratio threshold value.
  • the third threshold may be a threshold of 50% of the area of cells aggregated to the area of the cell area
  • the fourth threshold may be a threshold of 25% of the area of the cell area to the total area of the visual field.
  • the area and the pixel can be converted, and details are not repeated here.
  • FIG. 7 and 8 are schematic diagrams of the blood film tail according to an embodiment of the present invention
  • FIG. 7 is a schematic diagram of a relatively close to the blood film body
  • FIG. 8 is a schematic diagram of the tail edge close to the blank area.
  • cells especially red blood cells, will aggregate into clusters, and the cell area is small.
  • the dotted boxes in Figures 7 and 8 are clusters of cells.
  • the method further includes:
  • the control device determines the tail shooting path according to the target position of the tail
  • the control device causes the image capturing device and the blood smear to move relatively along the tail capturing path, so that the image capturing device captures a plurality of fourth target cell images on the tail capturing path.
  • the trailing shooting path is similar to the above-mentioned edge shooting path, as shown in FIG. 9 , can be E3-F3 parallel to the long edge of the blood smear, or can be G3-H3 perpendicular to the long edge of the blood smear.
  • the trailing shooting path is perpendicular to the long edge of the blood smear, which will not be repeated here.
  • whether the blood smear is abnormal can also be determined according to the target image of the tail, and the control device can output a plurality of first target cell images, a plurality of second target cell images and a plurality of second target cell images at the tail of the blood film.
  • the plurality of fourth target cell images in the tail are output to a display device, for example, so that the user can judge whether there are abnormal white blood cells or platelets in the blood smear according to the first target cell image, the second target cell image and the fourth target cell image Aggregation exceptions, etc.
  • control device can also automatically determine whether there is an abnormality in the blood smear according to the target image, that is, the method further includes:
  • the control device judges whether the blood smear has abnormal white blood cells according to the plurality of first target cell images and the plurality of second target cell images and the plurality of fourth target cell images at the long edge of the blood smear and/or platelet aggregation.
  • the position of the tail more precisely the position of the tail edge is searched when the edge area is photographed, and the embodiment of the present invention can also directly search for the position of the tail or the edge of the tail.
  • the region of interest includes the tail of the blood film
  • the control device determines the target position of the region of interest according to the image features and shooting positions of the multiple cell images, including:
  • the cell image taken first or last in the at least two cell images The shooting position is the first target position of the tail.
  • the initial shooting position and the final shooting position are respectively located outside the two edges of the tail of the blood film, such as A3, B3, or B3, A3 in FIG. 9; or
  • the initial shooting position is located in the tail of the blood film, and the final shooting position is located behind the tail along the smearing direction, such as C3, D3 in FIG. 9; or
  • the initial shooting position is located behind the tail in the smearing direction, and the final shooting position is in the tail of the blood film, such as D3 and C3 in FIG. 9 .
  • how to determine that the change of the image features of the at least two cell images taken successively indicates that the red blood cells are aggregated into clusters and/or the tail features of a small cell area are not repeated here.
  • the position of the tail edge can also be judged by changing the area size of the cell region of at least two cell images taken successively. For example, when the image capturing device continuously captures multiple cell images from the middle of the tail along the smear direction outwards, if the changes in these cell images indicate that the total area of the cell area begins to be smaller than the set threshold, it is considered that the tail part or tail edge of interest has been reached. For example, when the area of the cell region in the cell image begins to be less than 5% of the area of the entire image, it can be considered that there are few cell regions in the cell image and belong to the tail edge part.
  • multiple cell images 1900 may be taken from the body to the tail in a direction parallel to the long edge of the blood smear (in the direction of the arrow as shown) until a small number of cells, There are large voids, and/or tail regions where erythrocytes clump together.
  • the image position (number of images) of the tail area and the distance between adjacent images the actual distance from the shooting start point to the tail position is determined, and then the actual position of the tail edge is determined.
  • the tail edge is usually arc-shaped, multiple lines of shooting paths in the direction of the arrow can be selected to capture cell images, and multiple positions of the tail edge can be determined, so that the tail region can be more completely captured later.
  • the start and end points of each line of shooting paths can be preset and stored in the memory of the control device.
  • the image 1901 in Figure 19 is an actual position where the tail is located.
  • FIG. 20 it is also possible to photograph from one side to the other side (as shown by the arrow) perpendicular to the long edge of the blood smear to obtain a plurality of cell images 2000 , and find the upper and lower two The image position of the trailing edge. According to the image position (number of images) of the tail area and the distance between adjacent images, the actual distance from the shooting start point to the tail position is determined, and then the actual position of the tail edge is determined.
  • the tail edge is usually arc-shaped, multiple columns of shooting paths along the direction of the arrow can be selected for cell image shooting, and multiple positions of the tail edge can be determined, so that the tail region can be more completely captured later.
  • the start and end points of each column of shooting paths may be preset and stored in the memory of the control device; or the start and end points of the first column of shooting paths may be preset and stored in the memory of the control device, and the start and end points of subsequent shooting paths may be preset and stored in the memory of the control device.
  • the end point can be determined based on the position of the last detected trailing edge.
  • images 2001 and 2002 are both tail regions.
  • the method further includes:
  • the control device determines a first tail shooting path according to the first target position of the tail
  • the control device causes the image capturing device and the blood smear to move relatively along the first tail shooting path, so that the image capturing device shoots multiple images of the tail on the first tail shooting path.
  • a fourth target cell image is
  • another trailing edge position may be searched again, and after finding the trailing edge position, the shooting path may be adjusted to continue shooting the trailing trail.
  • the specific method is as follows:
  • the control device causes the image capturing device and the blood smear to move relatively along the first tail shooting path, so that the image capturing device shoots multiple images of the tail on the first tail shooting path.
  • the control device sequentially analyzes the image features of at least two images of the fourth target cell that are successively captured in the plurality of images of the fourth target cell,
  • the at least two fourth target cell images taken successively indicate that red blood cells are aggregated into clusters and/or tail features with small cell areas
  • the at least two fourth target cell images are taken first Or the shooting position of the fourth target cell image taken last is the second target position of the tail;
  • the control device determines, according to the second target position of the tail, a second trailing shooting path that is parallel/or perpendicular to the first trailing shooting path;
  • the control device causes the image capturing device and the blood smear to move relatively along the second tail shooting path, so that the image capturing device shoots multiple images of the tail on the second tail shooting path.
  • a fifth target cell image is
  • the first tail photographing path may be A4-B4, A4 is located outside the edge of the blood film tail, B4 is located in the blood film tail, and B4 corresponds to the tail in the image feature of the captured cell image.
  • the second target position is B4, with B4 as the starting point
  • the second shooting path can be B4-C4, and the C4 point is located outside the tail.
  • the tail edge of the blood film can be obtained. After obtaining the tail edge, you can move to point D4, and then continue to find the tail edge and take a picture of the tail along the path D4-E4.
  • the first tail photographing path may also be a path parallel to the long edge of the blood smear.
  • the method further includes:
  • the control device determines whether there is abnormal white blood cell and/or platelet aggregation in the blood smear according to the plurality of fourth target cell images and/or the plurality of fifth target cell images in the tail.
  • the line connecting the initial shooting position and the final shooting position is perpendicular to the edge of the blood smear.
  • the method further includes:
  • control device determines that there is abnormal platelet aggregation in the blood smear, estimate the blood smear according to at least one cell image of the long edge of the blood The number of platelets on the blood smear.
  • the target cell statistical method includes:
  • the cell image analysis device acquires the cell image of the blood sample, the blood sample originating from the blood sample to be tested;
  • the cell image analysis device automatically identifies the number of target cells and the number of reference cells in the cell image
  • the cell image analysis device obtains the number of the reference cells in the blood sample to be tested, and calculates the number of the reference cells based on the number of target cells and reference cells in the cell image, and the number of the reference cells in the blood sample to be tested. the number of target cells in the blood sample to be tested.
  • target cells can be platelets, red blood cells, white blood cells and the like.
  • target cells please refer to the application with the application number of PCT/CN2019/123029.
  • a plurality of cell pictures are taken first, and then analyzed.
  • analysis can be performed while taking pictures, as described below.
  • the method includes:
  • Step 2110 the control device acquires the starting shooting position and the preset moving direction of the cell shooting of the blood smear by the image shooting device;
  • Step 2120 the control device causes the image capture device to move relative to the blood smear, so that the image capture device starts from the starting capture point to capture the blood smear along the preset moving direction and analyze the cell images;
  • Step 2130 when the control device determines that the change of the image feature of the current cell image relative to the image feature of the cell image captured before or after the current cell image satisfies a third preset condition, then the current cell image The shooting position of is determined as the target position of the region of interest.
  • the control device determines that the change of the image feature of the current cell image relative to the image feature of the cell image captured before or after the current cell image satisfies the third preset condition, then the current cell image is captured by the control device.
  • the location is determined as the target location of the region of interest, including:
  • the control device identifies the cell area in the analyzed cell image according to the grayscale or color difference between the cell and the background in the analyzed cell image;
  • the capturing position of the current cell image is determined as the sensory The target location of the area of interest.
  • the region of interest is the long edge of the blood film
  • control device judges that the change of the image feature of the current cell image relative to the image feature of the cell image captured before or after the current cell image satisfies the third preset condition, then determines the shooting position of the current cell image as the sensor.
  • the target location of the area of interest including:
  • the shooting position of the current cell image is determined as the target position of the long edge of the blood membrane.
  • the method further includes:
  • the control device determines a first target shooting position according to the target position of the long edge
  • the control device causes the image capturing device to move relative to the blood smear, so as to position the image capturing device to the first target shooting position;
  • the control device causes the image capture device and the blood smear to continue to move relative to the first target capture position along a preset edge capture path, so that the image capture device captures the blood film.
  • the long edge takes a plurality of images of the first target cell along the path at the edge.
  • the method after shooting a plurality of first target cell images, the method includes:
  • the control device determines a second target shooting position according to the target position of the long edge, wherein the second target shooting position is different from the first target shooting position;
  • the control device causes the image capturing device to move relative to the blood smear, so as to position the image capturing device to the second target shooting position;
  • the control device causes the image capturing device and the blood smear to continue to move relative to the edge capturing path starting from the second target capturing position, so that the image capturing device captures the blood film. Multiple second target cell images along the long edge.
  • the region of interest is the tail of the blood film
  • control device judges that the change of the image feature of the current cell image relative to the image feature of the cell image captured before or after the current cell image satisfies the third preset condition, then determines the shooting position of the current cell image as the sensor.
  • the target location of the area of interest including:
  • the current cell image The shooting position is determined as the target position of the tail.
  • the method further includes:
  • the control device determines a first tail shooting path according to the target position of the tail
  • the control device causes the image capturing device and the blood smear to move relatively along the first tail shooting path, so that the image capturing device shoots multiple images of the tail on the first tail shooting path.
  • a fourth target cell image is
  • the method further includes:
  • the control device determines a second tail shooting path according to the target position of the tail
  • the control device causes the image capturing device and the blood smear to move relatively along the second tail shooting path, so that the image capturing device shoots multiple images of the tail on the second tail shooting path.
  • a fifth target cell image is
  • the starting position and ending position of the shooting path, the analysis process of the cell image, the analysis of abnormal cells after shooting the region of interest, etc. can refer to the solutions in other embodiments of the present invention, and will not be repeated here. .
  • real-time shooting and real-time analysis can be performed, and the shooting path can be adjusted in real time according to the analysis results, so that the region of interest can be located relatively quickly, and the positioning efficiency can be improved.
  • an embodiment of the present invention further provides a method for locating a region of interest, and the method includes:
  • Step 2210 the control device receives a mode selection instruction
  • Step 2220 when the mode selection instruction received by the control device is a dynamic mode, determine the target position of the region of interest according to the method of the above embodiment;
  • Step 2230 when the mode selection instruction received by the control device is a fixed mode, obtain a fixed preset target position of the region of interest;
  • Step 2240 The control device controls the image capturing device and the blood smear to move relatively according to the target position of the region of interest, so as to locate the target position of the region of interest.
  • the present invention also provides a method for locating a region of interest, which can be selected from two modes of shooting first and then analyzing, and two modes of analyzing while shooting, according to the default setting of the system or for setting.
  • the embodiment of the present invention also provides a cell image analyzer, as shown in FIG. 11 , including:
  • An image capturing device 1110 having a camera and a lens assembly, is used for capturing images of cells in the blood sample coated on the blood smear;
  • a smear moving device 1120 configured to relatively move the image capturing device and the blood smear
  • a control device 1130 connected in communication with the image capturing device and the smear moving device and configured to:
  • the target position of the region of interest is determined according to the image features and shooting positions of the plurality of cell images.
  • the embodiment of the present invention also provides a cell image analyzer, as shown in FIG. 11 , including:
  • an image capturing device 1110 having a camera and a lens group, for capturing images of cells in the blood sample coated on the blood smear;
  • a smear moving device 1120 configured to relatively move the image capturing device and the blood smear
  • a control device 1130 connected in communication with the image capturing device and the smear moving device and configured to:
  • the shooting position of the current cell image is determined as the region of interest. target location.
  • the above-mentioned cell image analyzer of the present invention is configured to implement the above-mentioned method.
  • the embodiment of the present invention also provides a cell image analyzer, as shown in FIG. 12 , including:
  • an image capturing device 1210 having a camera and a lens group, for capturing images of cells in the blood sample coated on the blood smear;
  • a smear moving device 1220 configured to relatively move the image capturing device and the blood smear
  • the mode selection device 1230 is used to select a dynamic mode or a fixed mode.
  • the target position of the region of interest can be dynamically confirmed according to different blood smears, and in the fixed mode, the sensor can be fixedly preset. the target location of the area of interest;
  • a control device 1240 in communication with the image capturing device, the smear moving device and the mode selection device and configured to:
  • the smear moving device is controlled so that the image capturing device and the blood smear move relative to each other, so as to locate the target position of the region of interest.
  • An embodiment of the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and running on the processor, where the processor implements the steps of the above method when the processor executes the computer program.
  • An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above method are performed.
  • the embodiment of the present invention also provides a sample analysis system.
  • the sample analysis system 100 includes a blood analyzer 110 , a smear preparation device 120 , a cell image analysis device 130 and a control device 140 .
  • the blood analyzer 110 is used for routine blood testing of the sample to be tested, the smear preparation device 120 is used to prepare the smear of the sample to be tested, the cell image analysis device 130 is used for image capturing and analysis of the cells in the smear, and the control device 140 is connected in communication with the blood analyzer 110 , the smear preparation device 120 and the cell image analysis device 130 .
  • the sample analysis system 100 further includes a first transport track 150 and a second transport track 160.
  • the first transport track 150 is used to transport the test tube rack 10 on which a plurality of test tubes 11 loaded with samples to be tested can be placed from the blood analyzer 110 to the coating device.
  • the second transport track 150 is used to transport the slide basket 20 , which can load a plurality of prepared smears 21 , from the smear preparation device 120 to the cell image analysis device 130 .
  • the control device 140 is electrically connected to the first transmission rail 150 and the second transmission rail 160 and controls the actions thereof.
  • the sample analysis system 100 further includes feeding mechanisms 170 and 180 corresponding to the blood analyzer 110 and the smear preparation device 120 respectively. and offload buffers 173 and 183.
  • the test tube rack 10 When the sample to be tested on the test tube rack 10 needs to be transported to the blood analyzer 110 for testing, the test tube rack 10 is first transported from the first transport track 150 to the loading buffer area 171 , and then transported from the loading buffer area 171 to the feeding The detection area 172 is detected by the blood analyzer 110 . After the detection, it is unloaded from the feed detection area 172 to the unloading buffer area 173 , and finally enters the first transport track 150 from the unloading buffer area 173 .
  • the test tube rack 10 needs to be transported to the smear preparation device 120 to prepare a smear.
  • the test tube rack 10 is first transported from the first transport track 150 to the loading buffer area. 181, and then transported from the loading buffer area 181 to the feeding detection area 182 to prepare smears by the smear preparation device 120. After the smear preparation is completed, it is unloaded from the feeding detection area 182 to the unloading buffer area 183, and finally again. From the unload buffer 183 into the first transfer track 150 .
  • the smear preparation device 120 stores the prepared smear in the glass slide basket 20 , and transports the glass slide basket 20 containing the smear to be tested to the cell image analysis device 130 through the second transmission track 160 , and the cell image analysis device 130 The cells in the sample on the smear to be tested are imaged and analyzed.
  • the sample analysis system 100 also includes a display device (not shown) for displaying sample detection results, which may be provided on the blood analyzer 110, the smear preparation device 120, the cell image analysis device 130, or the control device 140, or otherwise.
  • FIG. 24 and FIG. 25 are schematic diagrams showing the structure of the smear preparation device 120.
  • the smear preparation device 120 can be used for smear preparation of samples such as blood and body fluids.
  • the smear preparation device includes a sampling mechanism 121 for taking samples, a slide loading mechanism 122 for moving the slides to the working line, a sample loading mechanism 123 for loading the samples onto the slides, and a loading mechanism 123 for loading the slides onto the slides.
  • the slide pushing mechanism 124 for smoothing the sample
  • the drying mechanism (not shown in the figure) for drying the blood film on the glass slide
  • the staining mechanism 125 for staining the glass slide.
  • the sampling mechanism 121 extracts the sample, first mix the sample, and then use the sampling device (such as the sampling needle 1211) in the sampling mechanism 121 to aspirate the sample. body, the sampling device passes through the cover of the sample container), or it can be an open suction (the sample container is opened, and the sampling device directly aspirates the sample from the open part).
  • blood sample information testing can be performed to obtain information and comparison information.
  • a micro-sampling mechanism 126 is also included, and the micro-sampling mechanism 126 can directly move the test tube put in by the operator in the direction of the sampling device, or the sampling device can also move towards the direction of the test tube put in by the operator. direction move.
  • the micro-sampling mechanism 126 can also move the test tube directly in the direction of the sample-adding mechanism 123, or the sample-adding mechanism 123 can also move in the direction of the test tube put in by the operator, directly via the sample-adding mechanism 123 (for example, a blood drop needle) draws a blood sample and then loads the sample. Since there is no need to draw blood through the sampling mechanism 121, the need for blood samples can be reduced, thereby realizing micro and priority sample injection. When the sampling is completed, the blood is ready to be dropped onto the glass slide via the sample adding mechanism 123 .
  • the slide loading mechanism 122 extracts the slides and loads the slides to corresponding positions so as to facilitate the blood dripping operation.
  • operations such as left and right detection of the slides and cleaning of the slides may be performed, and then the slides are loaded.
  • the loaded slides can be printed with relevant information, and operations such as positive and negative slide detection can be performed at the same time.
  • the blood-dropping needle of the sample adding mechanism 123 drops the sample onto the glass slide and then performs a slide-pushing operation, and the slide-pushing mechanism 124 pushes the blood on the slide into the shape of a blood film.
  • the blood film on the slide can be dried to stabilize its shape.
  • the slide can be driven to turn over before drying the blood film to meet the corresponding requirements.
  • the dried blood smear can also be tested for drying to determine the drying effect of the blood film.
  • the dried blood smear can also be tested for blood film unfolding to determine whether the blood film is unfolded and whether the unfolded state meets the requirements.
  • the slide blood smear
  • the slide blood smear
  • directly output for example, placed in the slide basket 20 for output
  • the cell image analysis device 130 (also the cell image analyzer 130 ) includes at least an imaging device 131 , a smear moving device 132 and an image analysis device 133 , and the imaging device 131 includes a camera 1312 and a lens group 1311 And it is used to photograph the cells in the sample smeared on the smear, the smear moving device 132 is used to move the smear relative to the imaging device 131, so that the imaging device 131 can take a cell image of a specific area of the smear, the image analysis device 133 was used to analyze cell images of smears.
  • the lens group 1311 may include a first objective lens and a second objective lens.
  • the first objective lens may be, for example, a 10x objective lens
  • the second objective lens may be, for example, a 100x objective lens.
  • the lens group 1311 may further include a third objective lens, and the third objective lens may be, for example, a 40x objective lens.
  • the lens group 1311 may also include an eyepiece.
  • the cell image analysis device 130 further includes an identification device 134 , a slide gripping device 135 and a smear recovery device 136 .
  • the identification device 134 is used to identify the identity information of the smear
  • the slide clamping device 135 is used to clamp the smear from the identification device 134 to the smear moving device 132 for detection
  • the smear recovery device 136 is used to place the detected smear. smear.
  • the cell image analysis device 130 further includes a slide basket loading device 137 for loading the slide basket containing the smear to be tested, and the slide holding device 135 is also used for loading the slide basket loaded on the slide basket loading device 137
  • the glass slide to be tested in is clamped to the identification device 134 for identification information identification.
  • the slide basket loading device 137 is connected to the first transport track 160 so that the smear prepared by the smear preparation device 120 can be transported to the cell image analysis device 130 .
  • FIG. 13 it is a schematic structural diagram of a control apparatus provided by an embodiment of the present invention.
  • the control device 30 includes at least a processing component 31 , a RAM 112 , a ROM 113 , a communication interface 34 , a memory 36 and an I/O interface 35 , wherein the processing component 31 , the RAM 32 , the ROM 33 , the communication interface 34 , the memory 36 and the I/O interface 35 Communication takes place via bus 37 .
  • the processing component can be a CPU, a GPU or other chips with computing capabilities.
  • the memory 36 contains various computer programs, such as an operating system and an application program, which are executed by the processor unit 31, and data necessary for the execution of the computer programs. In addition, in the process of locating the region of interest, if necessary, locally stored data can be stored in the memory 36 .
  • the I/O interface 35 is composed of a serial interface such as USB, IEEE1394, or RS-232C, a parallel interface such as SCSI, IDE, or IEEE1284, and an analog signal interface composed of a D/A converter, an A/D converter, and the like.
  • An input device composed of a keyboard, a mouse, a touch screen or other control buttons is connected to the I/O interface 35 , and the user can directly input data to the control device 30 by using the input device.
  • the I/O interface 35 can also be connected to a display with a display function, such as a liquid crystal screen, a touch screen, an LED display screen, etc., and the control device 30 can output the processed data as image display data to the display for display, such as A first target cell image, a second target cell image, a third target cell image, a fourth target cell image, a fifth target cell image, and the like.
  • a display function such as a liquid crystal screen, a touch screen, an LED display screen, etc.
  • the communication interface 34 is an interface that may be any communication protocol currently known.
  • the communication interface 34 communicates with the outside world through a network.
  • the control device 30 can transmit data with any device connected through the network by a certain communication protocol through the communication interface 34 .

Landscapes

  • Chemical & Material Sciences (AREA)
  • Dispersion Chemistry (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Investigating Or Analysing Biological Materials (AREA)

Abstract

提供了一种定位血涂片上血膜的感兴趣区域的方法及细胞图像分析仪。该方法包括:控制装置获取图像拍摄装置对血涂片进行细胞拍摄的起始拍摄位置和最终拍摄位置,其中,该起始拍摄位置和最终拍摄位置的连线经过该感兴趣区域(101);控制装置使图像拍摄装置与血涂片发生相对移动,并使得图像拍摄装置从该起始拍摄点开始拍摄该血涂片的不同位置的多张细胞图像,直至最终拍摄位置停止相对移动和拍摄(102);控制装置根据该多张细胞图像的图像特征和拍摄位置,确定该感兴趣区域的目标位置(103)。这种分析仪便于用户更快、更准确的定位感兴趣区域,便于根据用户需求提高感兴趣区域的扫描面积。

Description

定位血涂片上血膜的感兴趣区域的方法和细胞图像分析仪 技术领域
本发明涉及医疗检测领域,具体涉及一种定位血涂片上血膜的感兴趣区域的方法及细胞图像分析仪。
背景技术
在医疗诊断领域,随着检验实验室自动化程度越来越高,对自动化检测的需求也越来越高。
全自动血细胞数字图像分析系统可以自动装卸血涂片、完成细胞定位及拍摄、细胞识别与预分类等功能,其检测速度和细胞图像质量大大提高,一定程度上可代替人工镜检的工作。现有的血细胞数字图像分析系统自动扫描血涂片,都是对血膜的体尾交接处进行扫描,该部位适合观察红细胞及白细胞。但是血小板聚集、大异常细胞等可能出现在血涂片的其他部位,只扫描体尾交接处存在漏检的风险。
发明内容
为了解决上述技术问题或者至少部分地解决上述技术问题,本申请提供了一种定位血涂片上血膜的感兴趣区域的方法及细胞图像分析仪,便于用户更快、更准确的定位感兴趣区域,便于根据用户需求提高感兴趣区域的扫描面积。
第一方面,本申请提供了一种定位血涂片上血膜的感兴趣区域的方法,所述方法包括:
控制装置获取图像拍摄装置对血涂片进行细胞拍摄的起始拍摄位置和最终拍摄位置,其中,所述起始拍摄位置和所述最终拍摄位置的连线经过所述感兴趣区域;
所述控制装置使所述图像拍摄装置与所述血涂片发生相对移动,并使得所述图像拍摄装置从所述起始拍摄点开始拍摄所述血涂片的不同位置的多张细胞图像,直至所述最终拍摄位置停止所述相对移动和拍摄;
所述控制装置根据所述多张细胞图像的图像特征和拍摄位置,确定所述感兴趣区域的目标位置。
第二方面,提供了一种定位血涂片上血膜的感兴趣区域的方法,所述方法包括:
控制装置获取图像拍摄装置对血涂片进行细胞拍摄的起始拍摄位置和预设移动方向;
所述控制装置使所述图像拍摄装置与所述血涂片发生相对移动,使所述图像拍摄装置从所述起始拍摄点开始沿所述预设移动方向拍摄所述血涂片的细胞图像并对所述细胞图像进行分析;
当所述控制装置判断当前细胞图像的图像特征相对于在所述当前细胞图像之前或之后拍摄的细胞图像的图像特征的变化满足第三预设条件时,则将所述当前细胞图像的拍摄位置确定为所述感兴趣区域的目标位置。
第三方面,提供了一种定位血涂片上血膜的感兴趣区域的方法,所述方法包括:
控制装置接收模式选择指令;
当所述控制装置接收到的模式选择指令为动态模式时,根据上述的方法确定所述感兴趣区域的目标位置;
当所述控制装置接收到的模式选择指令为固定模式时,获取固定预设的感兴趣区域的目标位置;
所述控制装置根据所述感兴趣区域的目标位置,控制所述图像拍摄装置和所述血涂片相对移动,以定位到所述感兴趣区域的目标位置。
第四方面,提供了一种细胞图像分析仪,包括:
图像拍摄装置,具有相机和透镜组,用于对血涂片上的血膜中的细胞进行图像拍摄;
涂片移动装置,用于使所述图像拍摄装置和所述血涂片相对移动;
控制装置,与所述图像拍摄装置和所述涂片移动装置通信连接并且配置用于:
获取所述图像拍摄装置对所述血涂片进行细胞拍摄的起始拍摄位置和最终拍摄位置,其中,所述起始拍摄位置和所述最终拍摄位置的连线经过所述血涂片的感兴趣区域;
控制所述涂片移动装置,使得所述图像拍摄装置与所述血涂片发生相对移动;
控制所述图像拍摄装置从所述起始拍摄点开始拍摄所述血涂片的不同位置的多张细胞图像,直至所述最终拍摄位置停止所述涂片移动装置和所述图像拍摄装置的动作;
根据所述多张细胞图像的图像特征和拍摄位置,确定所述感兴趣区域的目标位置。
第五方面,提供了一种细胞图像分析仪,包括:
图像拍摄装置,具有相机和透镜组,用于对血涂片上的血膜中的细胞进行图像拍摄;
涂片移动装置,用于使所述图像拍摄装置和所述血涂片相对移动;
控制装置,与所述图像拍摄装置和所述涂片移动装置通信连接并且配置用于:
获取所述图像拍摄装置对所述血涂片进行细胞拍摄的起始拍摄位置和预设移动方向;
控制所述涂片移动装置,使得所述图像拍摄装置与所述血涂片发生相对移动;
控制所述图像拍摄装置从所述起始拍摄点开始拍摄所述血涂片的细胞图像并对该细胞图像进行分析;
当判断当前细胞图像的图像特征相对于在该当前细胞图像之前或之后拍摄的细胞图像的图像特征的变化满足预设条件时,将所述当前细胞图像的拍摄位置确定为所述感兴趣区域的目标位置。
第六方面,提供了一种细胞图像分析仪,包括:
图像拍摄装置,具有相机和透镜组,用于对血涂片上的血膜中的细胞进行图像拍摄;
涂片移动装置,用于使所述图像拍摄装置和所述血涂片相对移动;
模式选择装置,用于选择动态模式或固定模式,在所述动态模式下能根据不同血涂片动态地确认其感兴趣区域的目标位置,而在所述固定模式下能固定地预设感兴趣区域的目标位置;
控制装置,与所述图像拍摄装置、所述涂片移动装置和所述模式选择装置通信连接并且配置用于:
从所述模式选择装置获取模式选择结果,
当选择了所述动态模式时,实施权利要求中任一项所述的方法,
当选择了所述固定模式时,获取固定预设的感兴趣区域的目标位置,
根据所述感兴趣区域的目标位置,控制所述涂片移动装置使得所述图像拍摄装置与所述血涂片发生相对移动,以定位到所述感兴趣区域的目标位置。
本发明实施例中,先从起始拍摄位置开始拍摄多张细胞图像,然后通过多张细胞图像特征和拍摄位置来确定感兴趣区域的目标位置,目标位置可以是血膜边界、例如血膜两侧长边边缘或血膜尾部边缘,解决了现有技术中还没有能够自动定位到血膜的两侧长边边缘或尾部边缘进行图像拍摄问题,便于用户更快、更准确的定位感兴趣区域,便于根据用户需求提高感兴趣区域的扫描面积。
附图说明
此处的附图被并入说明书中并构成本说明书的一部分,示出了符合本发明的实施例,并与说明书一起用于解释本发明的原理。
为了更清楚地说明本发明实施例或现有技术中的技术方案,下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍,显而易见地,对于本领域普通技术人员而言,在不付出创造性劳动性的前提下,还可以根据这些附图获得其他的附图。
图1所示为本发明实施例的定位感兴趣区域的方法的流程图;
图2所示为本发明实施例的血膜的示意图;
图3至图5所示为本发明实施例的细胞图像的示意图;
图6所示为本发明实施例的边缘拍摄路径的示意图;
图7、图8所示为本发明实施例的血膜尾部的示意图;
图9所示为本发明实施例的尾部拍摄路径的示意图;
图10所示为本发明实施例的拍摄路径的示意图;
图11、图12所示为本发明实施例的细胞图像分析仪的结构示意图;
图13所示为本发明实施例的控制装置的结构示意图;
图14至图16、19至20所示为本发明实施例的确认感兴趣区域的示意图;
图17至18、图21至22所示为本发明实施例的确认在确定了感兴趣区域的方法的流程图;
图23所示为本发明实施例的样本分析系统的示意图;
图24、图25所示为本发明实施例的涂片制备装置的结构示意图;
图26、图27所示为本发明实施例的细胞图像分析仪的结构示意图。
具体实施方式
为使本申请实施例的目的、技术方案和优点更加清楚,下面将结合本申请实施例中的附图,对本申请实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例是本申请的一部分实施例,而不是全部的实施例。基于本申请中的实施例,本领域普通技术人员在没有做出创造性劳动的前提下所获得的所有其他实施例,都属于本申请保护的范围。
本发明实施例提供了一种定位感兴趣区域的方法,应用细胞图像分析仪。其中,通过图像获取装置获取血涂片的不同拍摄位置的至少一张细胞图像,通过分析所述至少一张细胞图像是否满足预设条件(例如将图像中的特征与预设阈值做对比),判断是否找到了感兴趣区域,确定感兴趣区域在血涂片上的位置,以便后续准确拍摄感兴趣区域。也就是说,本发明实施例能够实现针对每个待测血涂片动态地确定感兴趣区域的位置、特别是血涂片上的血膜边界的位置,从而能够使图像获取装置准确地对血膜边界附近的区域进行拍摄。
图1所示为本发明实施例的定位血涂片上血膜的感兴趣区域的方法的流程图,所述方法包括:
步骤101,控制装置获取图像拍摄装置对血涂片进行细胞拍摄的起始拍摄位置和最终拍摄位置,其中,所述起始拍摄位置和所述最终拍摄位置的连线经过所述感兴趣区域;
步骤102,所述控制装置使所述图像拍摄装置与所述血涂片发生相对移动,并使得所述图像拍摄装置从所述起始拍摄点开始拍摄所述血涂片的不同位置的多张细胞图像,直至所述最终拍摄位置停止所述相对移动和拍摄;
步骤103,所述控制装置根据所述多张细胞图像的图像特征和拍摄位置,确定所述感兴趣区域的目标位置。
本发明实施例中,血涂片上具有血膜,该血涂片例如通过将血液样本涂覆在空白玻片上而形成,血膜为涂覆在血涂片上的血液形成的薄膜。如图2所示,血涂片通常是长方形的,血膜在血涂片上从A1端涂抹至B1端。血膜在涂抹过程中,沿涂抹方向,即如图2所示的从A1至B1端,可以包括头部、体部和尾部,分别以虚线框示出。血膜的边缘与血涂片的边缘之间可能有一定的间隙,例如血膜的长边边缘和血涂片的长边边缘之间的间隙C1。
本发明实施例中,感兴趣区域可以是血膜边缘,或可以是血膜的尾部,或可以是血膜边缘及血膜尾部。
本发明实施例中,先从起始拍摄位置和最终拍摄位置拍摄多张细胞图像,然后通过多张细胞图像特征和拍摄位置来确定感兴趣区域的目标位置,目标位置可以是边缘或尾部,解决了现有技术中还没有能够找到血膜的边界、例如血膜两侧长边边缘或尾部边缘的位置的问题,便于用户更快、更准确的定位感兴趣区域,便于根据用户需求提高感兴趣区域的扫描面积。
本发明实施例中,在拍摄多张细胞图像时,图像拍摄装置可以在不同的物镜下获取图像,例如在不小于40X(40倍)的物镜下获取细胞图像,优选为在100X(100倍)物镜下获取细胞图像。
本发明实施例中,步骤103中,所述控制装置使得图像拍摄装置从起始拍摄点开始拍摄所述血涂片的不同位置的多张细胞图像,包括:
所述控制装置使得所述图像拍摄装置从所述起始拍摄点开始按照预设图像间隔连续拍摄所述血涂片的不同位置的多张细胞图像。
本发明实施例中,预设图像间隔可以是时间间隔,或可以是距离间隔,在采用距离间隔时,优选方案可以是等间距。等间距拍摄时,前后两帧细胞图像可以是相接的连续拍摄,举例而言,此时的距离间隔可以 是成像装置的视野宽度或视野长度;或者,可以是有一定间距的间隔拍摄。
本发明实施例中,步骤103中,所述控制装置根据多张细胞图像的图像特征和拍摄位置,确定感兴趣区域的目标位置,包括:
所述控制装置依次分析所述多张细胞图像中先后拍摄、尤其是先后连续拍摄的至少两张细胞图像的图像特征;
若所述先后拍摄、尤其是先后连续拍摄的至少两张细胞图像的图像特征的变化满足第一预设条件,则所述至少两张细胞图像中的一张细胞图像的拍摄位置为所述感兴趣区域的目标位置。
本发明实施例中,步骤103中,所述图像特征包括细胞区域,所述先后拍摄的至少两张细胞图像的图像特征的变化满足第一预设条件,则至少两张细胞图像中的一张细胞图像的拍摄位置为所述感兴趣区域的目标位置,包括:
所述控制装置根据所分析的细胞图像中细胞和背景的灰度或颜色差异,识别所分析的细胞图像中的细胞区域;
若所述先后拍摄的至少两张细胞图像的细胞区域面积的变化满足第二预设条件,则所述至少两张细胞图像中的最先拍摄或最后拍摄细胞图像的拍摄位置为所述感兴趣区域的目标位置。
本发明实施例中,通常通过先后拍摄的、尤其是先后连续拍摄的至少两张细胞图像的图像特征的变化、例如细胞区域面积的变化来判断哪一帧细胞图像是感兴趣区域的目标位置。
本发明实施例中,所述感兴趣区域包括所述血膜的长边边缘;
所述先后拍摄的至少两张细胞图像的图像特征的变化满足第一预设条件,则至少两张细胞图像中的一张细胞图像的拍摄位置为所述感兴趣区域的目标位置,包括:
若所述先后拍摄的至少两张细胞图像中最先拍摄或最后拍摄的一张细胞图像的图像特征表示最先拍摄或最后拍摄的一张细胞图像对应部分空白部分细胞区域(如图4所示),且至少一张其余细胞图像的图像特征表示该其余细胞图像对应全空白区域(如图3所示)或全细胞区域(如图5所示),则所述最先拍摄或最后拍摄的细胞图像的拍摄位置为所述长边边缘的目标位置。
本实施例上述方法是根据图像特征变化来获取感兴趣区域。若是从部分空白部分细胞区域变化为全空白区域或全细胞区域,或者从全空白区域或全细胞区域变化为部分空白部分细胞区域,则部分空白部分细胞区域为长边边缘的目标位置。
本发明实施例中,控制装置分析细胞图像的图像特征,包括:
所述控制装置根据所述细胞图像中细胞和背景的灰度或颜色差异,识别所分析的细胞图像中的细胞区域;
若所述细胞图像的细胞区域的面积小于第一阈值,则所述细胞图像对应全空白区域,
若所述细胞图像的细胞区域的面积大于或等于第一阈值,则所述细胞图像对应部分空白部分细胞区域;和/或
若所述细胞图像的细胞区域的面积大于第二阈值,则所述细胞图像对应全细胞区域,
若所述细胞图像的细胞区域的面积小于或等于第二阈值,则所述细胞图像对应部分空白部分细胞区域。
本发明实施例中,第一阈值可以设置为0.01*视野总面积(整幅图像),即如果细胞图像的细胞区域的面积小于视野总面积的1%,则认为该细胞图像对应全空白区域;如果细胞区域的面积大于或等于视野总面积的1%,则认为细胞图像对应部分空白部分细胞区域。第二阈值可以设置为0.70*视野总面积,即如果细胞区域的面积大于视野总面积的70%,则认为该细胞图像对应全细胞区域;细胞区域小于或等于0.70*视野总面积的,该细胞图像对应部分空白部分细胞区域。可以理解的是,在实际使用中,由于血膜位置在可控范围内,因此能够大体确定起始拍摄点和拍摄方向,进而上述第一阈值和第二阈值可以单独作为判断部分空白部分细胞区域、全空白区域或全细胞区域的条件,比如从血膜的中部位置开始往长边边缘外拍摄的情况下,只需要判断从全细胞区域变化为部分空白部分细胞区域,即此时可以只使用第二阈值进行判断;同理,从长边边缘外往血膜中部位置拍摄的情况下,可以只使用第一阈值进行判断。当然,而其他可能实施例中,第一阈值和第二阈值也可以一起作为判断上述不同区域的条件,比如当细胞图像的细胞区域的面积介于视野总面积的1%至70%之间,则可认为该细胞图像对应部分空白部分细胞区域。举例而言,如果存在先后拍摄的多张细胞图像,第一张细胞图像的细胞区域面积占比大于70%(即处于全细胞区域),最后一张细胞图像的细胞区域面积占比开始小于1%(即进入完全空白区域),那么在最后一张细胞图像之前或之后拍摄的细胞图像所在的位置就是长边边缘。
需要说明的是,考虑到成像装置的视野总面积或细胞图像面积易于确定,第一阈值和/或第二阈值也可以表达为第一面积比阈值,例如第一阈值可以为细胞区域与视野总面积的面积比1%。
本发明实施例中,面积也可以是像素点个数,即面积、像素是可以转化的,例如细胞图像中一个像素代表0.05微米,则100微米是2000个像素;百分比也可以是固定的像素点个数(也就是面积大小),也是可 以相互转化的,比如整张图的像素点个数为5000000,则根据百分比1%计算阈值就是像素点个数50000。
如图3、图4、图5所示,图3所示的细胞图像为全空白区域的图像,图4所示为部分空白部分细胞区域的图像,图5所示为全细胞区域的图像。本发明实施例中,先通过细胞和背景的灰度或颜色差异,识别细胞区域,然后通过设置第一阈值和/或第二阈值,可以分析出细胞图像的图像特征,即可以分析出细胞图像对应的是全空白区域、部分空白部分细胞区域还是全细胞区域。
类似地,控制装置可以通过分析多张细胞图像中单张细胞图像的图像特征,来确定感兴趣区域的目标位置。本发明实施例的一种可能实现方式中,若所述任一细胞图像的图像特征表示细胞图像对应部分空白部分细胞区域时,则该任一细胞图像的拍摄位置为所述感兴趣区域包括所述血膜的长边边缘。例如通过前述方法分析某张细胞图像的图像特征,确定该细胞图像对应部分空白部分细胞区域时,即可确定该细胞图像拍摄的细胞图像所在的位置就是长边边缘。
本发明实施例的另一种可能实现方式中,通过对拍摄得到的多张细胞图像中的任意一张进行分析,比如依次分析或按其他顺序分析多张细胞图像,能够确定长边边缘。具体地,控制装置分析所述多张细胞图像中的任一细胞图像的图像特征,获取所述任一细胞图像的细胞区域的分布信息;若所述分布信息满足预设分布条件,则确定该任一细胞图像的拍摄位置为长边边缘的目标位置。由于在长边边缘的目标位置拍摄的细胞图像中,细胞区域会呈现从全细胞区域到部分空白部分细胞区域的分布,或从部分空白部分细胞区域到全空白区域的分布,或从全细胞区域到部分空白部分细胞区域的分布,或从部分空白部分细胞区域到全空白区域的分布,因此可将上述情况作为预设分布条件,确定长边边缘的目标位置。
在一种具体实现方式中,控制装置可通过分割所述多张细胞图像中的任一细胞图像,得到至少两张次生的细胞图像,分析所述两张次生的细胞图像的图像特征;若所述两张次生的细胞图像的图像特征分别表示所述两张次生的细胞图像中的一张对应全空白区域、另一张对应部分空白部分细胞区域或全细胞区域时;或者,若所述两张次生的细胞图像的图像特征分别表示所述两张次生的细胞图像中的一张对应全细胞区域、 另一张对应部分空白部分细胞区域或全空白区域时;则确定该任一细胞图像的拍摄位置为长边边缘的目标位置。
举例而言,可以在多张细胞图像中的任一细胞图像中预设至少一条分割线,得到至少两张由该任一细胞图像次生的细胞图像。优选地,分割线优先为平行于血涂片的边缘方向的直线;分割线可以定在该任一细胞图像的中间。分别计算分割出来的至少两张次生的细胞图像中细胞区域的面积,当次生的细胞图像的细胞区域的面积小于第一阈值,例如第一阈值为该次生的细胞图像总面积的1%,则可认为该次生的细胞图像对应全空白区域;当次生的细胞图像的细胞区域面积大于预定阈值,例如预定阈值为该次生的细胞图像总面积的50%(当然,预定阈值也可与第一阈值或第二阈值相同),则可认为该次生的细胞图像对应部分空白部分细胞区域或全细胞区域。由此,若所述两张次生的细胞图像的图像特征分别表示所述两张次生的细胞图像中的一张对应全空白区域、另一张对应部分空白部分细胞区域或全细胞区域时,则确定该任一细胞图像的拍摄位置为长边边缘的目标位置。
同理,也可通过前述的第一阈值和/或第二阈值来分别确定出次生的细胞图像对应全空白区域、部分空白部分细胞区域或全细胞区域。从而,若所述两张次生的细胞图像的图像特征分别表示所述两张次生的细胞图像中的一张对应全细胞区域、另一张对应部分空白部分细胞区域或全空白区域时;则确定该任一细胞图像的拍摄位置为长边边缘的目标位置。同前述实施例,第一阈值和第二阈值可以是固定值,也可以用细胞区域所占该次生的细胞图像的总面积的预设比例来确定。
需要说明的是,用成像装置拍摄的多张细胞图像中的单张细胞图像的图像特征来确定感兴趣区域的目标位置时,为避免漏检,前后拍摄的两张细胞图像的距离间隔小于成像装置的视野宽度或视野长度。具体地,该距离间隔可以与分割线的位置、第一阈值、第二阈值或预定阈值相匹配。例如,分割线定在中间时,连续两张图之间的距离可优选定为细胞图像视野宽度的50%。
本发明实施例中,所述起始拍摄位置和所述最终拍摄位置分别位于所述血膜的一个长边边缘的两侧,或者所述起始拍摄位置和所述最终拍摄位置分别位于所述血膜的两侧的长边边缘之外。所述血膜在所述血涂片上沿涂抹方向包括头部、体部和尾部,上述长边边缘为头部或体部的长边边缘。
参考图2所示,起始拍摄位置和最终拍摄位置可以是如D1、E1所示的位于血膜的一个长边边缘的两侧,或可以是如H1、F1所示的位于 血膜的另一个长边边缘的两侧,或可以是如D1、F1所示的分别位于血膜的两侧长边边缘之外。
参考图2所示,优选地,起始拍摄位置和最终拍摄位置可以是如G1、F1所示的位于血膜体部的两侧长边边缘之外,或者可以是如D1、I1所示的位于血膜头部的两侧长边边缘之外。
图2中的各位置仅为示意性的,D1、F1、G1、I1可以是位于血膜长边边缘与血涂片长边边缘之间如C1所示的任意位置,E1、H1可以是血膜之内的任意位置。上述起始拍摄位置和最终拍摄位置也可以互换。
在一个示例中,感兴趣区域为血膜的长边边缘,例如图2所示的血膜上边缘。起始拍摄位置和最终拍摄位置分别为E1和D1,即控制装置使图像拍摄装置从E1点开始按照预设图像间隔连续拍摄血涂片的不同位置的多张细胞图像,直至D1点。然后,控制装置对连续拍摄的多张细胞图像中先后连续拍摄的至少两张细胞图像的图像特征进行分析。若所述先后连续拍摄的至少两张细胞图像中最先拍摄的一张细胞图像为部分空白部分细胞区域(如图4所示),且至少一张其余细胞图像为全空白区域(如图3所示),则所述最先拍摄的细胞图像的拍摄位置为所述长边边缘的目标位置;或者,若所述先后连续拍摄的至少两张细胞图像中最后拍摄的一张细胞图像为部分空白部分细胞区域(如图4所示),且至少一张其余细胞图像为全细胞区域(如图5所示),则所述最后拍摄的细胞图像的拍摄位置为所述长边边缘的目标位置。也可以说,如图14所示,可从两侧空白位置往中间寻找边缘,沿垂直于血涂片长边边缘的方向(如图中箭头方向所示)拍摄多张图像1400,先是经过完全空白区域,然后是有空白有细胞的边缘区域,然后完全进入细胞区域。根据起始拍摄位置、边缘区域的图像位置(第几张)以及相邻图像的间隔距离,确定拍摄起点到边缘位置的实际距离,进而确定长边边缘所在的实际位置。图14中的图像1401所在之处即为长边边缘所在的一个实际位置。
在另一个示例中,也可从中间位置往两侧空白位置寻找边缘,如图15所示,沿垂直于血涂片长边边缘的方向(如图15中箭头方向所示)拍摄一系列图像1500,先是完全细胞区域,然后是有空白有细胞的边缘区域,然后完全进入空白区域;根据起始拍摄位置、边缘区域的图像位置(第几张)以及相邻图像的间隔距离,确定拍摄起点到边缘位置的实际距离,进而确定长边边缘所在的实际位置。图15中,图像1501即为长边边缘所在的一个实际位置。在又另一个示例中,感兴趣区域为血膜的两个长边边缘,例如图2所示的血膜上边缘和血膜下边缘。起始拍摄位置和最终拍摄位置分别为F1和G1,即控制装置使图像拍摄装置从F1点开始按照预设图像间隔连续拍摄血涂片的不同位置的多张细胞图像, 直至G1点。然后,控制装置对连续拍摄的多张细胞图像中先后连续拍摄的至少两张细胞图像的图像特征进行分析。若所述先后连续拍摄的至少两张细胞图像从部分空白部分细胞区域(如图4所示)变为全空白区域(如图3所示),或者从全细胞区域(如图5所示)变为部分空白部分细胞区域(如图4所示),则具有部分空白部分细胞区域的细胞图像的拍摄位置为血膜的长边边缘的目标位置。也就是说,可直接在从一侧空白位置拍摄到另外一侧空白位置,如图16,沿垂直于血涂片长边边缘的方向(如图16中箭头方向所示)拍摄一系列图像1600,进而定位到两侧的边缘位置。根据边缘区域的图像位置(第几张)以及相邻图像的间隔距离,确定拍摄起点到边缘位置的实际距离,进而确定边缘所在的实际位置。图16中,图像1601即为长边边缘所在的一个实际位置。
如图17所示,本发明实施例中,在确定了感兴趣区域的目标位置之后,所述方法还包括:
步骤1710,所述控制装置根据所述长边边缘的目标位置确定第一目标拍摄位置;
步骤1720,所述控制装置使所述图像拍摄装置与所述血涂片发生相对移动,以将所述图像拍摄装置定位到所述第一目标拍摄位置;
步骤1730,所述控制装置使所述图像拍摄装置与所述血涂片从所述第一目标拍摄位置出发沿着朝向所述尾部的边缘拍摄路径继续发生相对移动,使得所述图像拍摄装置拍摄所述血膜的长边边缘的多张第一目标细胞图像。
本发明实施例中,朝向所述尾部的边缘拍摄路径可以是平行于血涂片边缘,或平行于涂抹方向的路径。拍摄时,可以如上述实施例,按时间间隔或按照距离间隔拍摄。
本发明实施例中,还可以根据目标图像判断血涂片是否异常,所述方法还包括由控制装置输出所述血膜的长边边缘的多张第一目标细胞图像,例如输出到显示装置上,以便用户能够根据第一目标细胞图像判断血涂片是否存在异常白细胞、血小板聚集异常等。
备选地或附加地,还可以由控制装置自动根据目标图像判断血涂片是否存在异常,即所述方法还包括:
所述控制装置根据所述血膜的长边边缘的多张第一目标细胞图像判断所述血涂片是否存在异常白细胞和/或血小板聚集。
如图18所示,本发明实施例中,所述控制装置使得所述图像拍摄装置在拍摄多张第一目标细胞图像之后,所述方法还包括:
步骤1810,所述控制装置根据所述长边边缘的目标位置确定长边边缘的第二目标拍摄位置,其中,所述第二目标拍摄位置与所述第一目标 拍摄位置不同;
步骤1820,所述控制装置使所述图像拍摄装置与所述血涂片发生相对移动,以将所述图像拍摄装置定位到所述第二目标拍摄位置;
步骤1830,所述控制装置使所述图像拍摄装置与所述血涂片从所述第二目标拍摄位置出发与所述边缘拍摄路径平行地继续发生相对移动,使得所述图像拍摄装置拍摄所述血膜的长边边缘的多张第二目标细胞图像。
本发明实施例中,第二目标拍摄位置相比于第一目标拍摄位置在垂直于血涂片长边边缘的方向上(或者说垂直于涂抹方向上)与血涂片长边边缘相距更远,第一目标拍摄位置和第二目标拍摄位置的连线可以垂直于涂抹方向(血涂片长边边缘方向),或可以不垂直。
本发明实施例中,所述使得图像拍摄装置拍摄所述血膜的长边边缘的多张第二目标细胞图像之后,所述方法还包括:
判断所述多张第一目标图像和多张第二目标细胞图像的拍摄面积是否大于等于预设面积;
若大于等于预设面积,则停止拍摄;
若小于预设面积,则所述控制装置根据所述长边边缘的第三目标拍摄位置,使所述图像拍摄装置与所述血涂片从所述第三目标拍摄位置出发与所述边缘拍摄路径平行地继续发生相对移动,使得所述图像拍摄装置拍摄所述血膜的长边边缘的多张第三目标细胞图像,其中,所述第三目标拍摄位置与所述第二目标拍摄位置不同。
图6所述为本发明实施例的边缘拍摄路径的示意图,第一目标拍摄位置可以是A2点,边缘拍摄路径可以是A2-B2的路径。第二目标拍摄位置可以是C2点,对应的边缘拍摄路径可以是C2-D2。第二目标拍摄位置或可以是D2点,对应的边缘拍摄路径可以是D2-C2。
本发明实施例中,可以重复上述边缘拍摄路径多次,例如图6中的E2-F2等,直到拍摄的细胞图片的面积达到预设的面积,或者预定拍摄的总拍摄路径数,然后再进行拍摄。这样的目的是为了获得更多的边缘细胞的信息,以更准确地判断异常,例如血小板聚集等,此外,还可以充分考虑到因涂抹不规则或其他原因产生的血膜不规律的问题,便于用户更快、更准确的定位感兴趣区域,便于根据用户需求提高感兴趣区域的扫描面积。
本发明实施例中,还可以根据目标图像判断血涂片是否异常,所述方法还包括由控制装置输出所述血膜的长边边缘的多张第一目标细胞图像和多张第二目标细胞图像以及可选的第三目标细胞图像,例如输出到显示装置上,以便用户能够根据第一目标细胞图像和第二目标细胞图像 以及可选的第三目标细胞图像判断血涂片是否存在异常白细胞、血小板聚集异常等。
备选地或附加地,还可以由控制装置自动根据目标图像判断血涂片是否存在异常,即所述方法还包括:所述控制装置根据所述血膜的长边边缘的多张第一目标细胞图像和多张第二目标图像以及可选的多张第三目标图像判断所述血涂片是否存在异常白细胞和/或血小板聚集。
本发明实施例中,感兴趣区域还包括所述血膜的尾部,在拍摄血膜的长边边缘的同时能够对血膜的尾部进行识别,更准确地说,寻找尾部边缘,所述方法还包括:
所述控制装置依次分析所述多张第一目标细胞图像中先后拍摄的至少两张第一目标细胞图像的图像特征;
若所述先后拍摄的至少两张第一目标细胞图像的图像特征的变化表明出现红细胞聚集成团和/或细胞区域小的尾部特征或者说尾部边缘特征,则所述至少两张第一目标细胞图像中最后拍摄的第一目标细胞图像的拍摄位置为所述尾部的目标位置。
如图6所示,在长边边缘的图像拍摄过程中,是可能拍摄到尾部的,例如C2-D2后半段,或是F2-E2的后半段。
本发明实施例中,所述先后拍摄的至少两张第一目标细胞图像的图像特征的变化表明出现红细胞聚集成团和/或细胞区域小的尾部特征,包括:
所述先后拍摄的至少两张第一目标细胞图像中最后拍摄的第一目标细胞图像的红细胞聚集团数值特征大于第三阈值和/或细胞区域面积小于第四阈值,且其余至少一张第一目标细胞图像的红细胞聚集团数值特征小于等于所述第三阈值和/或细胞区域面积大于等于所述第四阈值。
也就是说,当先后拍摄的至少两张第一目标细胞图像的图像特征的变化表明细胞、例如红细胞聚集成团,且细胞区域总面积减少到设定阈值以下,则可以认为到达关注的尾部部分或者尾部边缘。
红细胞聚集团数值特征可以是红细胞聚集团的比例,或可以是红细胞聚集团的数量,或可以是面积大小。
本发明实施例中,第三阈值可以是0.5*细胞区域面积,第四阈值可以是0.25*视野总面积(整幅图像的面积),即,在细胞图像中,细胞区域的面积小于视野总面积的25%,和/或聚集成团的细胞面积与细胞区域的面积的比值超过阈值50%,则认为是到达了尾部边缘。这里聚集成团的判断方式是,该细胞块的连通域大小超过某阈值,比如200平方微米。
第三阈值、第四阈值也可以转化为第三面积比阈值、第四面积比阈值。例如第三阈值可以是聚集成团的细胞面积与细胞区域的面积比阈值 50%,第四阈值可以是细胞区域的面积与视野总面积的面积比阈值25%。
本发明实施例中,面积、像素是可以转化的,在此不再赘述。
图7、图8是本发明实施例的血膜尾部的示意图,图7为比较靠近血膜体部的示意图,图8位尾部边缘靠近空白区域的示意图。如图7、图8所示,在尾部区域,细胞、特别是红细胞会聚集成团,且细胞区域小,如图7、图8中的虚线框标出的即为细胞聚集而成的团。
本发明实施例中,所述方法还包括:
所述控制装置根据所述尾部的目标位置确定尾部拍摄路径;
所述控制装置使所述图像拍摄装置与所述血涂片沿着所述尾部拍摄路径发生相对移动,使得所述图像拍摄装置拍摄所述尾部拍摄路径上的多张第四目标细胞图像。
尾部拍摄路径与上述边缘拍摄路径相类似,如图9所示,可以是平行于血涂片长边边缘的E3-F3,或可以是垂直于血涂片长边边缘的G3-H3。优选尾部拍摄路径垂直于血涂片长边边缘,在此不再赘述。
类似地,本发明实施例中还可以根据尾部的目标图像判断血涂片是否异常,可以由控制装置输出所述血膜的尾部的多张第一目标细胞图像、多张第二目标细胞图像以及所述尾部的多张第四目标细胞图像,例如输出到显示装置上,以便用户能够根据第一目标细胞图像和第二目标细胞图像以及第四目标细胞图像判断血涂片是否存在异常白细胞、血小板聚集异常等。
备选地或附加地,还可以由控制装置自动根据目标图像判断血涂片是否存在异常,即所述方法还包括:
所述控制装置根据所述长边边缘的多张第一目标细胞图像和所述多张第二目标细胞图像和所述尾部的多张第四目标细胞图像判断所述血涂片是否存在异常白细胞和/或血小板聚集。
本发明上述实施例中,是在拍摄边缘区域的时候寻找尾部位置、更准确地说是尾部边缘位置,本发明实施例还可以直接寻找尾部或尾部边缘的位置。
亦即,本发明实施例中,所述感兴趣区域包括所述血膜的尾部;
所述控制装置根据多张细胞图像的图像特征和拍摄位置,确定感兴趣区域的目标位置,包括:
若所述先后拍摄的至少两张细胞图像的图像特征的变化表明出现红细胞聚集成团和/或细胞区域小的尾部特征,则所述至少两张细胞图像中最先拍摄或最后拍摄的细胞图像的拍摄位置为所述尾部的第一目标位置。
本发明实施例中,所述起始拍摄位置和所述最终拍摄位置分别位于所述血膜的尾部的两侧边缘之外,如图9中的A3、B3,或B3、A3;或 者
所述起始拍摄位置位于所述血膜的尾部中,而所述最终拍摄位置沿所述涂抹方向位于所述尾部之后,如图9中的C3、D3;或者
所述起始拍摄位置位于沿所述涂抹方向位于所述尾部之后,而所述最终拍摄位置所述血膜的尾部中,如图9中的D3、C3。
具体如何判断先后拍摄的至少两张细胞图像的图像特征的变化表明红细胞聚集成团和/或细胞区域小的尾部特征,在此不再赘述。
此外,也可以通过先后拍摄的至少两张细胞图像的细胞区域的面积大小变化来判断尾部边缘的位置。例如,当图像拍摄装置从尾部中间沿涂抹方向向外连续拍摄多张细胞图像时,如果这些细胞图像的变化表明细胞区域总面积开始小于设定阈值,就认为到达关注的尾部部分或尾部边缘。例如,当细胞图像中的细胞区域的面积开始小于整幅图像的面积的5%,则可认为该细胞图像中细胞区域很少,属于尾部边缘部分。
在一个示例中,如图19所示,可沿平行于血涂片长边边缘的方向(如图所示箭头的方向)从体部往尾部拍摄多张细胞图像1900,直到发现细胞数量少、存在大量空白,和/或红细胞聚集成团的尾部区域。根据尾部区域的图像位置(第几张)以及相邻图像的间隔距离,确定拍摄起点到尾部位置的实际距离,进而确定尾部边缘所在的实际位置。此外,由于尾部边缘通常呈弧形,因此可以选择多行沿箭头方向的拍摄路径进行细胞图像拍摄,确定尾部边缘的多个位置,以便后续能够较完整地拍摄尾部区域。每行拍摄路径的起点和终点可以预先设置并存储在控制装置的存储器中。图19中的图像1901即为尾部所在的一个实际位置。
在另一个示例中,如图20所示,也可沿垂直于血涂片长边边缘从一侧拍摄到另外一侧(如箭头所示),获取多张细胞图像2000,从中找到上下两个尾部边缘的图像位置。根据尾部区域的图像位置(第几张)以及相邻图像的间隔距离,确定拍摄起点到尾部位置的实际距离,进而确定尾部边缘所在的实际位置。此外,同样地,由于尾部边缘通常呈弧形,可以选择多列沿箭头方向的拍摄路径进行细胞图像拍摄,确定尾部边缘的多个位置,以便后续能够较完整地拍摄尾部区域。每列拍摄路径的起点和终点可以预先设置并存储在控制装置的存储器中;或者第一列拍摄路径的起点和终点可以预先设置并存储在控制装置的存储器中,而接着的拍摄路径的起点和终点可以根据上一次检测到的尾部边缘位置来确定。图20中,图像2001、2002均为尾部区域。
本发明实施例中,在确定尾部的目标位置之后,所述方法还包括:
所述控制装置根据所述尾部的第一目标位置确定第一尾部拍摄路径;
所述控制装置使所述图像拍摄装置与所述血涂片沿着所述第一尾部拍摄路径发生相对移动,使得所述图像拍摄装置拍摄所述尾部在所述第一尾部拍摄路径上的多张第四目标细胞图像。
本发明实施例中,还可以沿第一尾部路径拍摄的同时,再次寻找另一尾部边缘位置,在寻找到尾部边缘位置之后,调整拍摄路径,继续拍摄尾部。具体方法如下:
所述控制装置使所述图像拍摄装置与所述血涂片沿着所述第一尾部拍摄路径发生相对移动,使得所述图像拍摄装置拍摄所述尾部在所述第一尾部拍摄路径上的多张第四目标细胞图像;
所述控制装置依次分析所述多张第四目标细胞图像中先后拍摄的至少两张第四目标细胞图像的图像特征,
若所述先后拍摄的至少两张第四目标细胞图像的图像特征的变化表明出现红细胞聚集成团和/或细胞区域小的尾部特征,则所述至少两张第四目标细胞图像中最先拍摄或最后拍摄的第四目标细胞图像的拍摄位置为所述尾部的第二目标位置;
所述控制装置根据所述尾部的第二目标位置确定平行/或垂直于所述第一尾部拍摄路径的第二尾部拍摄路径;
所述控制装置使所述图像拍摄装置与所述血涂片沿着所述第二尾部拍摄路径发生相对移动,使得所述图像拍摄装置拍摄所述尾部在所述第二尾部拍摄路径上的多张第五目标细胞图像。
如图10所示,第一尾部拍摄路径可以是A4-B4,A4位于血膜尾部边缘之外,B4位于血膜尾部内,B4在拍摄的细胞图像的图像特征对应尾部。第二目标位置为B4,以B4为起点,第二拍摄路径可以是B4-C4,C4点位于尾部之外,在沿B4-C4拍摄的过程中,可以获取血膜的尾部边缘。获得了尾部边缘之后,可以移动至D4点,然后沿路径D4-E4继续寻找尾部边缘以及拍摄尾部图片。
图10所示的实施例中,第一尾部拍摄路径也可以是平行于血涂片长边边缘的路径。
本发明实施例中,所述方法还包括:
所述控制装置根据所述尾部的多张第四目标细胞图像和/或多张第五目标细胞图像判断所述血涂片是否存在异常白细胞和/或血小板聚集。
本发明实施例中,所述起始拍摄位置与所述最终拍摄位置的连线垂直于所述血涂片的边缘。
本发明实施例中,所述方法还包括:
当所述控制装置判断所述血涂片存在血小板聚集异常时,根据所述血膜的长边边缘的至少一张细胞图像和/或所述血膜的尾部的至少一张 细胞图像估计所述血涂片的血小板数量。
在本发明实施例中,目标细胞统计方法,包括:
细胞图像分析装置获取血液样本的细胞图像,所述血液样本源于待测血液样品;
所述细胞图像分析装置自动识别所述细胞图像中目标细胞数量和参考细胞数量;
所述细胞图像分析装置获取所述待测血液样品中所述参考细胞的数量,基于所述细胞图像中目标细胞数量和参考细胞数量、所述待测血液样品中所述参考细胞的数量计算所述待测血液样品中目标细胞的数量。
上述目标细胞可以是血小板,可以是红细胞、白细胞等。更具体的目标细胞统计方法,可参考申请号为PCT/CN2019/123029的申请。
本发明上述实施例中,是先拍摄多张细胞图片,然后进行分析,实际上,本发明实施例可以一边拍摄一边分析,如下所述。
如图21所示,本发明实施例中,所述方法包括:
步骤2110,控制装置获取图像拍摄装置对血涂片进行细胞拍摄的起始拍摄位置和预设移动方向;
步骤2120,所述控制装置使所述图像拍摄装置与所述血涂片发生相对移动,使所述图像拍摄装置从所述起始拍摄点开始沿所述预设移动方向拍摄所述血涂片的细胞图像并对所述细胞图像进行分析;
步骤2130,当所述控制装置判断当前细胞图像的图像特征相对于在所述当前细胞图像之前或之后拍摄的细胞图像的图像特征的变化满足第三预设条件时,则将所述当前细胞图像的拍摄位置确定为所述感兴趣区域的目标位置。
本发明实施例中,所述控制装置判断当前细胞图像的图像特征相对于在当前细胞图像之前或之后拍摄的细胞图像的图像特征的变化满足第三预设条件时,则将当前细胞图像的拍摄位置确定为所述感兴趣区域的目标位置,包括:
所述控制装置根据所分析的细胞图像中细胞和背景的灰度或颜色差异,识别所分析的细胞图像中的细胞区域;
若所述当前细胞图像的细胞区域相对于在该当前细胞图像之前或之后拍摄的细胞图像的细胞区域的面积变化满足第三预设条件,则将该当前细胞图像的拍摄位置确定为所述感兴趣区域的目标位置。
本发明实施例中,所述感兴趣区域为所述血膜的长边边缘;
所述控制装置判断当前细胞图像的图像特征相对于在当前细胞图像之前或之后拍摄的细胞图像的图像特征的变化满足第三预设条件时,则将当前细胞图像的拍摄位置确定为所述感兴趣区域的目标位置,包括:
若所述当前细胞图像的图像特征表示当前细胞图像对应部分空白部分细胞区域,且在所述当前细胞图像之前或之后拍摄的细胞图像的图像特征表示当前细胞图像之前或之后拍摄的细胞图像对应全空白区域或全细胞区域,则将所述当前细胞图像的拍摄位置确定为所述血膜的长边边缘的目标位置。
本发明实施例中,所述方法还包括:
所述控制装置根据所述长边边缘的目标位置确定第一目标拍摄位置;
所述控制装置使所述图像拍摄装置与所述血涂片发生相对移动,以将所述图像拍摄装置定位到所述第一目标拍摄位置;
所述控制装置使所述图像拍摄装置与所述血涂片从所述第一目标拍摄位置出发沿着预设的边缘拍摄路径继续发生相对移动,使得所述图像拍摄装置拍摄所述血膜的长边边缘在所述边缘拍摄路径上的多张第一目标细胞图像。
本发明实施例中,所述在拍摄多张第一目标细胞图像之后,所述方法包括:
所述控制装置根据所述长边边缘的目标位置确定第二目标拍摄位置,其中,所述第二目标拍摄位置与第一目标拍摄位置不同;
所述控制装置使所述图像拍摄装置与所述血涂片发生相对移动,以将所述图像拍摄装置定位到所述第二目标拍摄位置;
所述控制装置使所述图像拍摄装置与所述血涂片从所述第二目标拍摄位置出发与所述边缘拍摄路径平行地继续发生相对移动,使得所述图像拍摄装置拍摄所述血膜的长边边缘的多张第二目标细胞图像。
本发明实施例中,所述感兴趣区域为所述血膜的尾部;
所述控制装置判断当前细胞图像的图像特征相对于在当前细胞图像之前或之后拍摄的细胞图像的图像特征的变化满足第三预设条件时,则将当前细胞图像的拍摄位置确定为所述感兴趣区域的目标位置,包括:
若所述当前细胞图像的图像特征相对于在该当前细胞图像之前或之后拍摄的细胞图像的图像特征的变化表明出现红细胞聚集成团和/或细胞区域小的尾部特征,则将该当前细胞图像的拍摄位置确定为所述尾部的目标位置。
本发明实施例中,所述方法还包括:
所述控制装置根据所述尾部的目标位置确定第一尾部拍摄路径;
所述控制装置使所述图像拍摄装置与所述血涂片沿着所述第一尾部拍摄路径发生相对移动,使得所述图像拍摄装置拍摄所述尾部在所述第一尾部拍摄路径上的多张第四目标细胞图像。
本发明实施例中,所述方法还包括:
所述控制装置根据所述尾部的目标位置确定第二尾部拍摄路径;
所述控制装置使所述图像拍摄装置与所述血涂片沿着所述第二尾部拍摄路径发生相对移动,使得所述图像拍摄装置拍摄所述尾部在所述第二尾部拍摄路径上的多张第五目标细胞图像。
本实施例中,拍摄路径的起始位置、结束位置、细胞图像的分析过程、对感兴趣区域拍摄后的细胞异常的分析等,可以参上本发明其他实施例中的方案,在此不再赘述。
本发明上述实施例中,可以实时拍摄实时分析,根据分析结果实时调整拍摄路径,可以较为迅速地定位感兴趣区域,提高定位效率。
如图22所示,本发明实施例还提供了一种定位感兴趣区域的方法,所述方法包括:
步骤2210,控制装置接收模式选择指令;
步骤2220,当所述控制装置接收到的模式选择指令为动态模式时,根据上述实施例的方法确定所述感兴趣区域的目标位置;
步骤2230,当所述控制装置接收到的模式选择指令为固定模式时,获取固定预设的感兴趣区域的目标位置;
步骤2240,所述控制装置根据所述感兴趣区域的目标位置,控制所述图像拍摄装置和所述血涂片相对移动,以定位到所述感兴趣区域的目标位置。
本发明还提供了一种定位感兴趣区域的方法,可以根据系统默认设置,或者用于设置,在先拍摄后分析,以及边拍摄边分析两种模式中进行选择。
本发明实施例还提供了一种细胞图像分析仪,如图11所示,包括:
图像拍摄装置1110,具有相机和透镜组并,用于对血涂片上涂覆的血液样本中的细胞进行图像拍摄;
涂片移动装置1120,用于使所述图像拍摄装置和所述血涂片相对移动;
控制装置1130,与所述图像拍摄装置和所述涂片移动装置通信连接并且配置用于:
获取所述图像拍摄装置对所述血涂片进行细胞拍摄的起始拍摄位置和最终拍摄位置,其中,所述起始拍摄位置和所述最终拍摄位置的连线经过所述血涂片的感兴趣区域;
控制所述涂片移动装置,使得所述图像拍摄装置与所述血涂片发生相对移动;
控制所述图像拍摄装置从所述起始拍摄点开始拍摄所述血涂片的不同位置的多张细胞图像,直至所述最终拍摄位置停止所述涂片移动装置和所述图像拍摄装置的动作;
根据所述多张细胞图像的图像特征和拍摄位置,确定所述感兴趣区域的目标位置。
本发明实施例还提供了一种细胞图像分析仪,参照图11所示,包括:
图像拍摄装置1110,具有相机和透镜组,用于对血涂片上涂覆的血液样本中的细胞进行图像拍摄;
涂片移动装置1120,用于使所述图像拍摄装置和所述血涂片相对移动;
控制装置1130,与所述图像拍摄装置和所述涂片移动装置通信连接并且配置用于:
获取所述图像拍摄装置对所述血涂片进行细胞拍摄的起始拍摄位置和预设移动方向;
控制所述涂片移动装置,使得所述图像拍摄装置与所述血涂片发生相对移动;
控制所述图像拍摄装置从所述起始拍摄点开始拍摄所述血涂片的细胞图像并对该细胞图像进行分析;
当判断当前细胞图像的图像特征相对于在该当前细胞图像之前或之后拍摄的细胞图像的图像特征的变化满足预设条件时,将所述当前细胞图像的拍摄位置确定为所述感兴趣区域的目标位置。
本发明上述细胞图像分析仪,配置用于实施上述方法。
本发明实施例还提供了一种细胞图像分析仪,如图12所示,包括:
图像拍摄装置1210,具有相机和透镜组,用于对血涂片上涂覆的血液样本中的细胞进行图像拍摄;
涂片移动装置1220,用于使所述图像拍摄装置和所述血涂片相对移动;
模式选择装置1230,用于选择动态模式或固定模式,在所述动态模式下能根据不同血涂片动态地确认其感兴趣区域的目标位置,而在所述固定模式下能固定地预设感兴趣区域的目标位置;
控制装置1240,与所述图像拍摄装置、所述涂片移动装置和所述模式选择装置通信连接并且配置用于:
从所述模式选择装置获取模式选择结果,
当选择了所述动态模式时,实施上述的方法,
当选择了所述固定模式时,获取固定预设的感兴趣区域的目标位置,
根据所述感兴趣区域的目标位置,控制所述涂片移动装置使得所述 图像拍摄装置与所述血涂片发生相对移动,以定位到所述感兴趣区域的目标位置。
本发明实施例还提供了一种计算机设备,包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序,所述处理器执行所述计算机程序时实现上述方法的步骤。
本发明实施例还提供了一种计算机可读存储介质,其上存储有计算机程序,所述计算机程序被处理器执行时上述方法的步骤。
本发明实施例还提供了一种样本分析系统。如图23所示,样本分析系统100包括血液分析仪110、涂片制备装置120、细胞图像分析装置130和控制装置140。
血液分析仪110用于对待测样本进行血常规检测,涂片制备装置120用于制备待测样本的涂片,细胞图像分析装置130用于对涂片中的细胞进行图像拍摄和分析,控制装置140与血液分析仪110、涂片制备装置120和细胞图像分析装置130通信连接。
样本分析系统100还包括第一传输轨道150和第二传输轨道160,第一传输轨道150用于将可放置多个装载有待测样本的试管11的试管架10从血液分析仪110运送至涂片制备装置120,第二传输轨道150用于将可装载多个制备好的涂片21的玻片篮20从涂片制备装置120运送至细胞图像分析装置130。
控制装置140与第一传输轨道150和第二传输轨道160电连接并控制其动作。
样本分析系统100还包括分别对应于血液分析仪110和涂片制备装置120设置的进给机构170和180,各进给机构170和180包括装载缓存区171和181、进给检测区172和183以及卸载缓存区173和183。
当试管架10上的待测样本需要被运送至血液分析仪110进行检测时,试管架10首先从第一传输轨道150被运送到装载缓存区171,然后从装载缓存区171被运送到进给检测区172由血液分析仪110进行检测,在检测结束之后,再从进给检测区172被卸载到卸载缓存区173,最后再从卸载缓存区173进入第一传输轨道150。
同理,当试管架10上的待测样本需要进行镜检时,需要将试管架10运送至涂片制备装置120制备涂片,试管架10首先从第一传输轨道150被运送到装载缓存区181,然后从装载缓存区181被运送到进给检测区182由涂片制备装置120制备涂片,在涂片制备结束之后,再从进给检测区182被卸载到卸载缓存区183,最后再从卸载缓存区183进入第一传输轨道150。涂片制备装置120将制备好的涂片收纳在玻片篮20中,通过第二传输轨道160将收纳有待测涂片的玻片篮20运送至细胞图像分 析装置130,细胞图像分析装置130对待测涂片上的样本中的细胞进行图像拍摄并进行分析。
样本分析系统100还包括用于显示样本检测结果的显示装置(未示出),可设置在血液分析仪110、涂片制备装置120、细胞图像分析装置130或控制装置140上,或者另外设置。
图24和图25示出涂片制备装置120的结构示意图,涂片制备装置120可用于血液、体液等样本的涂片制备。该涂片制备装置包括用于抽取样本的取样机构121、用于将玻片移至工作线的玻片装载机构122、用于将样本加载到玻片的加样机构123、用于将玻片上的样本抹平的推片机构124、用于对玻片上血膜进行干燥的干燥机构(图中未标示出)以及用于对玻片进行染色的染色机构125。
取样机构121进行样本提取时,先进行样本混匀,然后利用取样机构121中的采样装置(例如采样针1211)吸样,根据样本容器的不同,吸样可以是穿刺吸样(样本容器具有盖体,采样装置穿过样本容器的盖体),也可以是开放吸样(样本容器敞开,采样装置直接从敞口部吸样)。必要时,可进行血样信息检测,以获取信息和比对信息。某些实施例中,还包括微量进样机构126,该微量进样机构126可以将操作人员放入的试管直接向采样装置的方向移动,或者,采样装置也可以向操作人员放入的试管的方向移动。其他实现方式中,微量进样机构126还可以将试管直接向加样机构123的方向移动,或者,加样机构123也可以向操作人员放入的试管的方向移动,直接经由加样机构123(例如滴血针)吸取血样后进行样本加载,由于无需通过取样机构121抽取血液,可以减少血样的需求,从而实现微量及优先进样。当取样完成后,经由加样机构123准备将血液滴落到玻片上。
相应地,玻片装载机构122提取玻片,并将玻片装载到相应位置,以便于进行滴血操作。一些实施例中,在完成提取玻片操作后,还可以进行玻片左右检测和玻片清洁等操作,之后再装载玻片。装载后的玻片可以打印相关信息,同时进行玻片正反检测等操作。
加样机构123的滴血针将样本滴落到玻片上后进行推片操作,通过推片机构124将血液在玻片上推成血膜形状。通常,在完成推片动作后,可对玻片上的血膜进行干燥,稳定其形态。在一些实施例中,可在对进行血膜干燥前,驱动玻片翻转,以满足相应需求。一些实施例中,干燥后的血涂片还可进行干燥检测,用来判定血膜干燥效果。一些实施例中,干燥后的血涂片还可以进行血膜展开检测,用以判断血膜是否展开以及展开状态是否符合要求。推片完成后玻片(血涂片)可进行染色(可通过染色机构125实现)或者直接输出(例如放置到玻片篮20内输出)
如图26和图27所示,细胞图像分析装置130(也成细胞图像分析仪130)至少包括成像装置131、涂片移动装置132和图像分析装置133,成像装置131包括相机1312和透镜组1311并且用于对涂片上涂抹的样本中的细胞进行拍摄,涂片移动装置132用于使涂片相对于成像装置131运动,以便成像装置131拍摄涂片的特定区域的细胞图像,图像分析装置133用于对涂片的细胞图像进行分析。
如图27所示,透镜组1311可以包括第一物镜和第二物镜。第一物镜例如可以为10倍物镜,第二物镜例如可以为100倍物镜。透镜组1311还可以包括第三物镜,第三物镜例如可以为40倍物镜。透镜组1311还可以包括目镜。
细胞图像分析装置130还包括识别装置134、玻片夹取装置135和涂片回收装置136。识别装置134用于识别涂片的身份信息,玻片夹取装置135用于将涂片从识别装置134夹取到涂片移动装置132上进行检测,涂片回收装置136用于放置经检测的涂片。
细胞图像分析装置130还包括玻片篮装载装置137,用于装载装有待测涂片的玻片篮,玻片夹取装置135还用于将玻片篮装载装置137上装载的玻片篮中的待测玻片夹取到识别装置134进行身份信息识别。玻片篮装载装置137与第一传输轨道160连接,以便由涂片制备装置120制备的涂片能够运送至细胞图像分析装置130。
在一个实施例中,如图13所示,为本发明实施例提供的一种控制装置的结构示意图。该控制装置30至少包括:处理组件31、RAM112、ROM113、通信接口34、存储器36和I/O接口35,其中,处理组件31、RAM32、ROM33、通信接口34、存储器36和I/O接口35通过总线37进行通信。
处理组件可以为CPU,GPU或其它具有运算能力的芯片。
存储器36中装有操作系统和应用程序等供处理器组件31执行的各种计算机程序及执行该计算机程序所需的数据。另外,在定位感兴趣区域的过程中,如有需要本地存储的数据,均可以存储到存储器36中。
I/O接口35由比如USB、IEEE1394或RS-232C等串行接口、SCSI、IDE或IEEE1284等并行接口以及由D/A转换器和A/D转换器等组成的模拟信号接口构成。I/O接口35上连接有由键盘、鼠标、触摸屏或其它控制按钮构成的输入设备,用户可以用输入设备直接向控制装置30输入数据。另外,I/O接口35上还可以连接由具有显示功能的显示器,例如:液晶屏、触摸屏、LED显示屏等,控制装置30可以将处理的数据以图像显示数据输出到显示器上进行显示,例如第一目标细胞图像、第二目标细胞图像、第三目标细胞图像、第四目标细胞图像、第五目标细胞图 像等。
通信接口34是可以是目前已知的任意通信协议的接口。通信接口34通过网络与外界进行通信。控制装置30可以通过通信接口34以一定的通信协议,与通过该网连接的任意装置之间传输数据。
需要说明的是,在本文中,诸如“第一”和“第二”等之类的关系术语仅仅用来将一个实体或者操作与另一个实体或操作区分开来,而不一定要求或者暗示这些实体或操作之间存在任何这种实际的关系或者顺序。而且,术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含,从而使得包括一系列要素的过程、方法、物品或者设备不仅包括那些要素,而且还包括没有明确列出的其他要素,或者是还包括为这种过程、方法、物品或者设备所固有的要素。在没有更多限制的情况下,由语句“包括一个……”限定的要素,并不排除在包括所述要素的过程、方法、物品或者设备中还存在另外的相同要素。
以上在说明书、附图以及权利要求中所提及的特征,只要在本发明内是有意义的并且不会相互矛盾,均可任意相互组合。针对按照本发明的方法所描述的特征和优点以相应的方式适用于按照本发明的细胞图像分析仪,反之亦然。
以上所述仅是本发明的具体实施方式,使本领域技术人员能够理解或实现本发明。对这些实施例的多种修改对本领域的技术人员来说将是显而易见的,本文中所定义的一般原理可以在不脱离本发明的精神或范围的情况下,在其它实施例中实现。因此,本发明将不会被限制于本文所示的这些实施例,而是要符合与本文所申请的原理和新颖特点相一致的最宽的范围。

Claims (39)

  1. 一种定位血涂片上血膜的感兴趣区域的方法,其特征在于,所述方法包括:
    控制装置获取图像拍摄装置对血涂片进行细胞拍摄的起始拍摄位置和最终拍摄位置,其中,所述起始拍摄位置和所述最终拍摄位置的连线经过所述感兴趣区域;
    所述控制装置使所述图像拍摄装置与所述血涂片发生相对移动,并使得所述图像拍摄装置从所述起始拍摄点开始拍摄所述血涂片的不同位置的多张细胞图像,直至所述最终拍摄位置停止所述相对移动和拍摄;
    所述控制装置根据所述多张细胞图像的图像特征和拍摄位置,确定所述感兴趣区域的目标位置。
  2. 如权利要求1所述的方法,其特征在于,所述控制装置使得图像拍摄装置从起始拍摄点开始拍摄血涂片的不同位置的多张细胞图像,包括:
    所述控制装置使得所述图像拍摄装置从所述起始拍摄点开始按照预设图像间隔连续拍摄所述血涂片的不同位置的多张细胞图像。
  3. 如权利要求1或2所述的方法,其特征在于,所述控制装置根据多张细胞图像的图像特征和拍摄位置,确定感兴趣区域的目标位置,包括:
    所述控制装置依次分析所述多张细胞图像中先后拍摄的至少两张细胞图像的图像特征;
    若所述先后拍摄的至少两张细胞图像的图像特征的变化满足第一预设条件,则所述至少两张细胞图像中的一张细胞图像的拍摄位置为所述感兴趣区域的目标位置。
  4. 如权利要求3所述的方法,其特征在于,所述图像特征包括细胞区域,所述先后拍摄的至少两张细胞图像的图像特征的变化满足第一预设条件,则至少两张细胞图像中的一张细胞图像的拍摄位置为所述感兴趣区域的目标位置,包括:
    所述控制装置根据所分析的细胞图像中细胞和背景的灰度或颜色差 异,识别所分析的细胞图像中的细胞区域;
    若所述先后拍摄的至少两张细胞图像的细胞区域面积的变化满足第二预设条件,则所述至少两张细胞图像中的最先拍摄或最后拍摄细胞图像的拍摄位置为所述感兴趣区域的目标位置。
  5. 如权利要求3或4所述的方法,其特征在于,所述感兴趣区域包括所述血膜的长边边缘;
    所述先后拍摄的至少两张细胞图像的图像特征的变化满足第一预设条件,则至少两张细胞图像中的一张细胞图像的拍摄位置为所述感兴趣区域的目标位置,包括:
    若所述先后拍摄的至少两张细胞图像中最先拍摄或最后拍摄的一张细胞图像的图像特征表示所述最先拍摄或最后拍摄的一张细胞图像对应部分空白部分细胞区域,且至少一张其余细胞图像的图像特征表示所述其余细胞图像对应全空白区域或全细胞区域,则所述最先拍摄或最后拍摄的细胞图像的拍摄位置为所述长边边缘的目标位置。
  6. 如权利要求1所述的方法,其特征在于,所述感兴趣区域包括所述血膜的长边边缘;所述控制装置根据多张细胞图像的图像特征和拍摄位置,确定感兴趣区域的目标位置,包括:
    所述控制装置分析所述多张细胞图像中任一细胞图像的图像特征;
    若所述任一细胞图像的图像特征表示细胞图像对应部分空白部分细胞区域时,则该任一细胞图像的拍摄位置为所述感兴趣区域的目标位置。
  7. 如权利要求1所述的方法,其特征在于,所述感兴趣区域包括所述血膜的长边边缘;所述控制装置根据多张细胞图像的图像特征和拍摄位置,确定感兴趣区域的目标位置,包括:
    所述控制装置分析所述多张细胞图像中的任一细胞图像的图像特征,获取所述任一细胞图像的细胞区域的分布信息;
    若所述分布信息满足预设分布条件,则确定该任一细胞图像的拍摄位置为长边边缘的目标位置。
  8. 如权利要求5或6或7所述的方法,其特征在于,所述控制装置 分析细胞图像的图像特征,包括:
    所述控制装置根据所述细胞图像中细胞和背景的灰度或颜色差异,识别所分析的细胞图像中的细胞区域;
    若所述细胞图像的细胞区域的面积小于第一阈值,则所述细胞图像对应全空白区域,若所述细胞图像的细胞区域的面积大于或等于第一阈值,则所述细胞图像对应部分空白部分细胞区域;和/或,
    若所述细胞图像的细胞区域的面积大于第二阈值,则所述细胞图像对应全细胞区域,若所述细胞图像的细胞区域的面积小于或等于第二阈值,则所述细胞图像对应部分空白部分细胞区域。
  9. 如权利要求8所述的方法,其特征在于,所述起始拍摄位置和所述最终拍摄位置分别位于所述血膜的一个长边边缘的两侧,或者所述起始拍摄位置和所述最终拍摄位置分别位于所述血膜的两侧的长边边缘之外。
  10. 如权利要求9所述的方法,其特征在于,所述血膜在所述血涂片上沿涂抹方向包括头部、体部和尾部,所述长边边缘为头部或体部的长边边缘。
  11. 如权利要求1至10中任一项所述的方法,其特征在于,所述血膜在所述血涂片上沿涂抹方向包括头部、体部和尾部,所述方法还包括:
    所述控制装置根据所述长边边缘的目标位置确定长边边缘的第一目标拍摄位置;
    所述控制装置使所述图像拍摄装置与所述血涂片发生相对移动,以将所述图像拍摄装置定位到所述第一目标拍摄位置;
    所述控制装置使所述图像拍摄装置与所述血涂片从所述第一目标拍摄位置出发沿着朝向所述尾部的边缘拍摄路径继续发生相对移动,使得所述图像拍摄装置拍摄所述血膜的长边边缘的多张第一目标细胞图像。
  12. 如权利要求11所述的方法,其特征在于,所述控制装置使得所述图像拍摄装置在拍摄多张第一目标细胞图像之后,所述方法还包括:
    所述控制装置根据所述长边边缘的目标位置确定长边边缘的第二目标拍摄位置,其中,所述第二目标拍摄位置与所述第一目标拍摄位置不 同;
    所述控制装置使所述图像拍摄装置与所述血涂片发生相对移动,以将所述图像拍摄装置定位到所述第二目标拍摄位置;
    所述控制装置使所述图像拍摄装置与所述血涂片从所述第二目标拍摄位置出发与所述边缘拍摄路径平行地继续发生相对移动,使得所述图像拍摄装置拍摄所述血膜的长边边缘的多张第二目标细胞图像。
  13. 如权利要求12所述的方法,其特征在于,所述使得图像拍摄装置拍摄所述血膜的长边边缘的多张第二目标细胞图像之后,所述方法还包括:
    判断所述多张第一目标图像和多张第二目标细胞图像的拍摄面积是否大于等于预设面积;
    若大于等于预设面积,则停止拍摄;
    若小于预设面积,则所述控制装置根据所述长边边缘的第三目标拍摄位置,使所述图像拍摄装置与所述血涂片从所述第三目标拍摄位置出发与所述边缘拍摄路径平行地继续发生相对移动,使得所述图像拍摄装置拍摄所述血膜的长边边缘的多张第三目标细胞图像,其中,所述第三目标拍摄位置与所述第二目标拍摄位置不同。
  14. 如权利要求11至13中任一项所述的方法,其特征在于,所述方法还包括:
    所述控制装置输出所述血膜的长边边缘的多张第一目标细胞图像和/或多张第二目标图像和/或多张第三目标细胞图像;和/或
    所述控制装置根据所述血膜的长边边缘的多张第一目标细胞图像和/或多张第二目标图像和/或多张第三目标细胞图像判断所述血涂片是否存在异常白细胞和/或血小板聚集。
  15. 如权利要求11至14中任一项所述的方法,其特征在于,所述感兴趣区域还包括所述血膜的尾部,所述方法还包括:
    所述控制装置依次分析所述多张第一目标细胞图像中先后拍摄的至少两张第一目标细胞图像的图像特征;
    若所述先后拍摄的至少两张第一目标细胞图像的图像特征的变化表 明出现红细胞聚集成团和/或细胞区域小的尾部特征,则所述至少两张第一目标细胞图像中最后拍摄的第一目标细胞图像的拍摄位置为所述尾部的目标位置。
  16. 如权利要求15所述的方法,其特征在于,所述先后拍摄的至少两张第一目标细胞图像的图像特征的变化表明出现红细胞聚集成团和/或细胞区域小的尾部特征,包括:
    所述先后拍摄的至少两张第一目标细胞图像中最后拍摄的第一目标细胞图像的红细胞聚集团数值特征大于第三阈值和/或细胞区域面积小于第四阈值,且其余至少一张第一目标细胞图像的红细胞聚集团数值特征小于等于所述第三阈值和/或细胞区域面积大于等于所述第四阈值。
  17. 如权利要求15或16所述的方法,其特征在于,所述方法还包括:
    所述控制装置根据所述尾部的目标位置确定尾部拍摄路径;
    所述控制装置使所述图像拍摄装置与所述血涂片沿着所述尾部拍摄路径发生相对移动,使得所述图像拍摄装置拍摄所述尾部拍摄路径上的多张第四目标细胞图像。
  18. 如权利要求17所述的方法,其特征在于,所述方法还包括:
    所述控制装置输出所述血膜的长边边缘的多张第一目标细胞图像和/或多张第二目标图像和/或所述尾部的多张第四目标细胞图像;和/或
    所述控制装置根据所述长边边缘的多张第一目标细胞图像和/或所述多张第二目标细胞图像和/或所述尾部的多张第四目标细胞图像判断所述血涂片是否存在异常白细胞和/或血小板聚集。
  19. 如权利要求4或5所述的方法,其特征在于,所述血膜在血涂片上沿涂抹方向包括头部、体部和尾部,所述感兴趣区域包括所述血膜的尾部;
    所述控制装置根据多张细胞图像的图像特征和拍摄位置,确定感兴趣区域的目标位置,包括:
    若所述先后拍摄的至少两张细胞图像的图像特征的变化表明出现红细胞聚集成团和/或细胞区域小的尾部特征,则所述至少两张细胞图像中 最先拍摄或最后拍摄的细胞图像的拍摄位置为所述尾部的第一目标位置。
  20. 如权利要求19所述的方法,其特征在于,所述起始拍摄位置和所述最终拍摄位置分别位于所述血膜的尾部的两侧边缘之外;或者
    所述起始拍摄位置位于所述血膜的尾部中,而所述最终拍摄位置沿所述涂抹方向位于所述尾部之后;或者
    所述起始拍摄位置位于沿所述涂抹方向位于所述尾部之后,而所述最终拍摄位置所述血膜的尾部中。
  21. 如权利要求19或20所述的方法,其特征在于,所述先后拍摄的至少两张细胞图像的图像特征的变化表明出现红细胞聚集成团和/或细胞区域小的尾部特征,包括:
    所述先后拍摄的至少两张细胞图像中最先拍摄或最后拍摄的细胞图像的红细胞聚集团数值特征大于第三阈值和/或细胞区域面积小于第四阈值,且至少一张其余细胞图像的红细胞聚集团数值特征小于等于所述第三阈值和/或细胞区域面积大于等于所述第四阈值。
  22. 如权利要求19至21中任一项所述的方法,其特征在于,所述方法还包括:
    所述控制装置根据所述尾部的第一目标位置确定第一尾部拍摄路径;
    所述控制装置使所述图像拍摄装置与所述血涂片沿着所述第一尾部拍摄路径发生相对移动,使得所述图像拍摄装置拍摄所述尾部在所述第一尾部拍摄路径上的多张第四目标细胞图像。
  23. 如权利要求22所述的方法,其特征在于,所述方法还包括:
    所述控制装置输出所述尾部的多张第四目标细胞图像;和/或所述控制装置根据所述尾部的多张第四目标细胞图像判断所述血涂片是否存在异常白细胞和/或血小板聚集。
  24. 如权利要求9或10所述的方法,其特征在于,所述起始拍摄位置与所述最终拍摄位置的连线垂直于所述血涂片的边缘。
  25. 如权利要求14或18或23所述的方法,其特征在于,所述方法还包括:
    所述控制装置根据所述血膜的长边边缘的至少一张目标细胞图像和 /或所述血膜的尾部的至少一张目标细胞图像估计所述血涂片的血小板数量。
  26. 一种定位血涂片上血膜的感兴趣区域的方法,其特征在于,所述方法包括:
    控制装置获取图像拍摄装置对血涂片进行细胞拍摄的起始拍摄位置和预设移动方向;
    所述控制装置使所述图像拍摄装置与所述血涂片发生相对移动,使所述图像拍摄装置从所述起始拍摄点开始沿所述预设移动方向拍摄所述血涂片的细胞图像并对所述细胞图像进行分析;
    当所述控制装置判断当前细胞图像的图像特征相对于在所述当前细胞图像之前或之后拍摄的细胞图像的图像特征的变化满足第三预设条件时,则将所述当前细胞图像的拍摄位置确定为所述感兴趣区域的目标位置。
  27. 如权利要求16所述的方法,其特征在于,所述控制装置判断当前细胞图像的图像特征相对于在当前细胞图像之前或之后拍摄的细胞图像的图像特征的变化满足第三预设条件时,则将当前细胞图像的拍摄位置确定为所述感兴趣区域的目标位置,包括:
    所述控制装置根据所分析的细胞图像中细胞和背景的灰度或颜色差异,识别所分析的细胞图像中的细胞区域;
    若所述当前细胞图像的细胞区域相对于在该当前细胞图像之前或之后拍摄的细胞图像的细胞区域的面积变化满足第三预设条件,则将该当前细胞图像的拍摄位置确定为所述感兴趣区域的目标位置。
  28. 如权利要求26或27所述的方法,其特征在于,所述感兴趣区域为所述血膜的长边边缘;
    所述控制装置判断当前细胞图像的图像特征相对于在当前细胞图像之前或之后拍摄的细胞图像的图像特征的变化满足第三预设条件时,则将当前细胞图像的拍摄位置确定为所述感兴趣区域的目标位置,包括:
    若所述当前细胞图像的图像特征表示所述当前细胞图像对应部分空白部分细胞区域,且在所述当前细胞图像之前或之后拍摄的细胞图像的 图像特征表示所述在当前细胞图像之前或之后拍摄的细胞图像对应全空白区域或全细胞区域,则将所述当前细胞图像的拍摄位置确定为所述血膜的长边边缘的目标位置。
  29. 如权利要求26至28中任一项所述的方法,其特征在于,所述方法还包括:
    所述控制装置根据所述长边边缘的目标位置确定第一目标拍摄位置;
    所述控制装置使所述图像拍摄装置与所述血涂片发生相对移动,以将所述图像拍摄装置定位到所述第一目标拍摄位置;
    所述控制装置使所述图像拍摄装置与所述血涂片从所述第一目标拍摄位置出发沿着预设的边缘拍摄路径继续发生相对移动,使得所述图像拍摄装置拍摄所述血膜的长边边缘在所述边缘拍摄路径上的多张第一目标细胞图像。
  30. 如权利要求29所述的方法,其特征在于,在所述图像拍摄装置拍摄所述多张第一目标细胞图像之后,所述方法包括:
    所述控制装置根据所述长边边缘的目标位置确定第二目标拍摄位置,其中,所述第二目标拍摄位置与第一目标拍摄位置不同;
    所述控制装置使所述图像拍摄装置与所述血涂片发生相对移动,以将所述图像拍摄装置定位到所述第二目标拍摄位置;
    所述控制装置使所述图像拍摄装置与所述血涂片从所述第二目标拍摄位置出发与所述边缘拍摄路径平行地继续发生相对移动,使得所述图像拍摄装置拍摄所述血膜的长边边缘的多张第二目标细胞图像。
  31. 如权利要求26或27所述的方法,其特征在于,所述血膜在血涂片上沿涂抹方向包括头部、体部和尾部,所述感兴趣区域为所述血膜的尾部;
    所述控制装置判断当前细胞图像的图像特征相对于在当前细胞图像之前或之后拍摄的细胞图像的图像特征的变化满足第三预设条件时,则将当前细胞图像的拍摄位置确定为所述感兴趣区域的目标位置,包括:
    若所述当前细胞图像的图像特征相对于在该当前细胞图像之前或之后拍摄的细胞图像的图像特征的变化表明出现红细胞聚集成团和/或
    细胞区域小的尾部特征,则将该当前细胞图像的拍摄位置确定为所述尾部的目标位置。
  32. 如权利要求31所述的方法,其特征在于,所述方法还包括:
    所述控制装置根据所述尾部的目标位置确定第一尾部拍摄路径;
    所述控制装置使所述图像拍摄装置与所述血涂片沿着所述第一尾部拍摄路径发生相对移动,使得所述图像拍摄装置拍摄所述尾部在所述第一尾部拍摄路径上的多张第四目标细胞图像。
  33. 如权利要求32所述的方法,其特征在于,所述方法还包括:
    所述控制装置根据所述尾部的目标位置确定第二尾部拍摄路径;
    所述控制装置使所述图像拍摄装置与所述血涂片沿着所述第二尾部拍摄路径发生相对移动,使得所述图像拍摄装置拍摄所述尾部在所述第二尾部拍摄路径上的多张第五目标细胞图像。
  34. 一种定位血涂片上血膜的感兴趣区域的方法,其特征在于,所述方法包括:
    控制装置接收模式选择指令;
    当所述控制装置接收到的模式选择指令为动态模式时,根据权利要求1至33中任一项所述的方法确定所述感兴趣区域的目标位置;
    当所述控制装置接收到的模式选择指令为固定模式时,获取固定预设的感兴趣区域的目标位置;
    所述控制装置根据所述感兴趣区域的目标位置确定所述感兴趣区域的拍摄路径。
  35. 一种细胞图像分析仪,其特征在于,包括:
    图像拍摄装置,具有相机和透镜组,用于对血涂片上的血膜中的细胞进行图像拍摄;
    涂片移动装置,用于使所述图像拍摄装置和所述血涂片相对移动;
    控制装置,与所述图像拍摄装置和所述涂片移动装置通信连接并且配置用于:
    获取所述图像拍摄装置对所述血涂片进行细胞拍摄的起始拍摄位置和最终拍摄位置,其中,所述起始拍摄位置和所述最终拍摄位置的连线 经过所述血涂片的感兴趣区域;
    控制所述涂片移动装置,使得所述图像拍摄装置与所述血涂片发生相对移动;
    控制所述图像拍摄装置从所述起始拍摄点开始拍摄所述血涂片的不同位置的多张细胞图像,直至所述最终拍摄位置停止所述涂片移动装置和所述图像拍摄装置的动作;
    根据所述多张细胞图像的图像特征和拍摄位置,确定所述感兴趣区域的目标位置。
  36. 根据权利要求35所述的细胞图像分析仪,其特征在于,所述控制装置进一步配置用于实施权利要求2至34中任一项所述的方法。
  37. 一种细胞图像分析仪,其特征在于,包括:
    图像拍摄装置,具有相机和透镜组,用于对血涂片上的血膜中的细胞进行图像拍摄;
    涂片移动装置,用于使所述图像拍摄装置和所述血涂片相对移动;
    控制装置,与所述图像拍摄装置和所述涂片移动装置通信连接并且配置用于:
    获取所述图像拍摄装置对所述血涂片进行细胞拍摄的起始拍摄位置和预设移动方向;
    控制所述涂片移动装置,使得所述图像拍摄装置与所述血涂片发生相对移动;
    控制所述图像拍摄装置从所述起始拍摄点开始拍摄所述血涂片的细胞图像并对该细胞图像进行分析;
    当判断当前细胞图像的图像特征相对于在该当前细胞图像之前或之后拍摄的细胞图像的图像特征的变化满足预设条件时,将所述当前细胞图像的拍摄位置确定为感兴趣区域的目标位置。
  38. 根据权利要求37所述的细胞图像分析仪,其特征在于,所述控制装置进一步配置用于实施权利要求26至33中任一项所述的方法。
  39. 一种细胞图像分析仪,其特征在于,包括:
    图像拍摄装置,具有相机和透镜组,用于对血涂片上的血膜中的细 胞进行图像拍摄;
    涂片移动装置,用于使所述图像拍摄装置和所述血涂片相对移动;
    模式选择装置,用于选择动态模式或固定模式,在所述动态模式下能根据不同血涂片动态地确认其感兴趣区域的目标位置,而在所述固定模式下能固定地预设感兴趣区域的目标位置;
    控制装置,与所述图像拍摄装置、所述涂片移动装置和所述模式选择装置通信连接并且配置用于:
    从所述模式选择装置获取模式选择结果,
    当选择了所述动态模式时,实施权利要求1至33中任一项所述的方法,
    当选择了所述固定模式时,获取固定预设的感兴趣区域的目标位置,
    根据所述感兴趣区域的目标位置,控制所述涂片移动装置使得所述图像拍摄装置与所述血涂片发生相对移动,以定位到所述感兴趣区域的目标位置。
PCT/CN2020/112526 2020-08-31 2020-08-31 定位血涂片上血膜的感兴趣区域的方法和细胞图像分析仪 WO2022041210A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2020/112526 WO2022041210A1 (zh) 2020-08-31 2020-08-31 定位血涂片上血膜的感兴趣区域的方法和细胞图像分析仪
CN202080104241.4A CN116097083A (zh) 2020-08-31 2020-08-31 定位血涂片上血膜的感兴趣区域的方法和细胞图像分析仪

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/112526 WO2022041210A1 (zh) 2020-08-31 2020-08-31 定位血涂片上血膜的感兴趣区域的方法和细胞图像分析仪

Publications (1)

Publication Number Publication Date
WO2022041210A1 true WO2022041210A1 (zh) 2022-03-03

Family

ID=80354343

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/112526 WO2022041210A1 (zh) 2020-08-31 2020-08-31 定位血涂片上血膜的感兴趣区域的方法和细胞图像分析仪

Country Status (2)

Country Link
CN (1) CN116097083A (zh)
WO (1) WO2022041210A1 (zh)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1945326A (zh) * 2006-10-13 2007-04-11 江西特康科技有限公司 基于视觉形态的五分类全血细胞分析方法
US20110151502A1 (en) * 2009-12-22 2011-06-23 Abbott Laboratories Method for performing a blood count and determining the morphology of a blood smear
US10345218B2 (en) * 2016-12-06 2019-07-09 Abbott Laboratories Automated slide assessments and tracking in digital microscopy
CN110647875A (zh) * 2019-11-28 2020-01-03 北京小蝇科技有限责任公司 一种血细胞分割、识别模型构造的方法及血细胞识别方法
CN111062346A (zh) * 2019-12-21 2020-04-24 电子科技大学 一种白细胞自动定位检测及分类识别系统及方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1945326A (zh) * 2006-10-13 2007-04-11 江西特康科技有限公司 基于视觉形态的五分类全血细胞分析方法
US20110151502A1 (en) * 2009-12-22 2011-06-23 Abbott Laboratories Method for performing a blood count and determining the morphology of a blood smear
US10345218B2 (en) * 2016-12-06 2019-07-09 Abbott Laboratories Automated slide assessments and tracking in digital microscopy
CN110647875A (zh) * 2019-11-28 2020-01-03 北京小蝇科技有限责任公司 一种血细胞分割、识别模型构造的方法及血细胞识别方法
CN111062346A (zh) * 2019-12-21 2020-04-24 电子科技大学 一种白细胞自动定位检测及分类识别系统及方法

Also Published As

Publication number Publication date
CN116097083A (zh) 2023-05-09

Similar Documents

Publication Publication Date Title
JP5470625B2 (ja) 粒子画像解析方法および装置
WO2021109152A1 (zh) 样本分析系统及方法、细胞图像分析仪及存储介质
WO2012169088A1 (ja) 画像処理装置、画像処理方法及び画像処理システム
EP3811287A2 (en) System and method for detection and classification of objects of interest in microscope images by supervised machine learning
US20150356342A1 (en) Image processing apparatus, image processing method, and storage medium
US20230251205A1 (en) Sample testing method and sample analyzer
WO2021134664A1 (zh) 一种样本分析系统及其自动精度管理方法
WO2022041210A1 (zh) 定位血涂片上血膜的感兴趣区域的方法和细胞图像分析仪
US8538122B2 (en) Localization of a valid area of a blood smear
CN105115797A (zh) 血液推片机、血涂片制备方法、确定推片参数的装置及方法
WO2014196097A1 (ja) 画像処理システム、画像処理装置、プログラム、記憶媒体及び画像処理方法
CN112213503A (zh) 样本分析系统、图像分析系统及其处理样本图像的方法
US20220334100A1 (en) Sample analyzing system, method and cell image analyzing device
WO2021136484A1 (zh) 细胞图像分析装置和样本分析方法
Rupp et al. Fully automated detection of the counting area in blood smears for computer aided hematology
WO2023031622A1 (en) System and method for identifying and counting biological species
WO2021102984A1 (zh) 一种涂片制备装置、样本分析系统及方法
CN111337696B (zh) 一种体外诊断设备及其样本分析方法
US20220291196A1 (en) Target cell statistical method, apparatus, and system
CN114829944A (zh) 样本分析系统及方法
WO2021135393A1 (zh) 一种图像分析装置及其成像方法
CN115266481A (zh) 细胞图像分析系统以及细胞图像分析方法
US11796787B2 (en) Sample image capturing system and method, and computer-readable storage medium
CN112469984A (zh) 一种图像分析装置及其成像方法
CN114858796A (zh) 样本图像分析系统和玻片质量检测方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20950879

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20950879

Country of ref document: EP

Kind code of ref document: A1