WO2021109152A1 - 样本分析系统及方法、细胞图像分析仪及存储介质 - Google Patents

样本分析系统及方法、细胞图像分析仪及存储介质 Download PDF

Info

Publication number
WO2021109152A1
WO2021109152A1 PCT/CN2019/123819 CN2019123819W WO2021109152A1 WO 2021109152 A1 WO2021109152 A1 WO 2021109152A1 CN 2019123819 W CN2019123819 W CN 2019123819W WO 2021109152 A1 WO2021109152 A1 WO 2021109152A1
Authority
WO
WIPO (PCT)
Prior art keywords
cell
tested
blood
cell image
sample
Prior art date
Application number
PCT/CN2019/123819
Other languages
English (en)
French (fr)
Inventor
祁欢
李朝阳
叶燚
叶波
邢圆
罗玮
余珊
陈巧妮
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/CN2019/123819 priority Critical patent/WO2021109152A1/zh
Priority to EP19955311.6A priority patent/EP4071485A4/en
Priority to CN201980102379.8A priority patent/CN114729953A/zh
Publication of WO2021109152A1 publication Critical patent/WO2021109152A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N35/00—Automatic analysis not limited to methods or materials provided for in any single one of groups G01N1/00 - G01N33/00; Handling materials therefor
    • G01N35/00029—Automatic analysis not limited to methods or materials provided for in any single one of groups G01N1/00 - G01N33/00; Handling materials therefor provided with flat sample substrates, e.g. slides
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N1/00—Sampling; Preparing specimens for investigation
    • G01N1/28—Preparing specimens for investigation including physical details of (bio-)chemical methods covered elsewhere, e.g. G01N33/50, C12Q
    • G01N1/2813—Producing thin layers of samples on a substrate, e.g. smearing, spinning-on
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
    • G01N15/02—Investigating particle size or size distribution
    • G01N15/0205—Investigating particle size or size distribution by optical means
    • G01N15/0227—Investigating particle size or size distribution by optical means using imaging; using holography
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
    • G01N15/10—Investigating individual particles
    • G01N15/1031—Investigating individual particles by measuring electrical or magnetic effects
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
    • G01N15/10—Investigating individual particles
    • G01N15/14—Optical investigation techniques, e.g. flow cytometry
    • G01N15/1429—Signal processing
    • G01N15/1433—Signal processing using image recognition
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N35/00—Automatic analysis not limited to methods or materials provided for in any single one of groups G01N1/00 - G01N33/00; Handling materials therefor
    • G01N35/00584—Control arrangements for automatic analysers
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N35/00—Automatic analysis not limited to methods or materials provided for in any single one of groups G01N1/00 - G01N33/00; Handling materials therefor
    • G01N35/00584—Control arrangements for automatic analysers
    • G01N35/00722—Communications; Identification
    • G01N35/00871—Communications between instruments or with remote terminals
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
    • G01N2015/0092—Monitoring flocculation or agglomeration
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
    • G01N15/01—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials specially adapted for biological cells, e.g. blood cells
    • G01N2015/018—Platelets
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
    • G01N15/02—Investigating particle size or size distribution
    • G01N2015/0294—Particle shape
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
    • G01N15/10—Investigating individual particles
    • G01N2015/1006—Investigating individual particles for cytology
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
    • G01N15/10—Investigating individual particles
    • G01N2015/1019—Associating Coulter-counter and optical flow cytometer [OFC]
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
    • G01N15/10—Investigating individual particles
    • G01N2015/1024—Counting particles by non-optical means
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
    • G01N15/10—Investigating individual particles
    • G01N15/14—Optical investigation techniques, e.g. flow cytometry
    • G01N2015/1486—Counting the particles
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
    • G01N15/10—Investigating individual particles
    • G01N15/14—Optical investigation techniques, e.g. flow cytometry
    • G01N2015/1493—Particle size
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
    • G01N15/10—Investigating individual particles
    • G01N15/14—Optical investigation techniques, e.g. flow cytometry
    • G01N2015/1497—Particle shape
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N35/00—Automatic analysis not limited to methods or materials provided for in any single one of groups G01N1/00 - G01N33/00; Handling materials therefor
    • G01N35/00029—Automatic analysis not limited to methods or materials provided for in any single one of groups G01N1/00 - G01N33/00; Handling materials therefor provided with flat sample substrates, e.g. slides
    • G01N2035/00039—Transport arrangements specific to flat sample substrates, e.g. pusher blade
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N35/00—Automatic analysis not limited to methods or materials provided for in any single one of groups G01N1/00 - G01N33/00; Handling materials therefor
    • G01N35/00029—Automatic analysis not limited to methods or materials provided for in any single one of groups G01N1/00 - G01N33/00; Handling materials therefor provided with flat sample substrates, e.g. slides
    • G01N2035/00099—Characterised by type of test elements
    • G01N2035/00138—Slides
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N35/00—Automatic analysis not limited to methods or materials provided for in any single one of groups G01N1/00 - G01N33/00; Handling materials therefor
    • G01N35/02—Automatic analysis not limited to methods or materials provided for in any single one of groups G01N1/00 - G01N33/00; Handling materials therefor using a plurality of sample containers moved by a conveyor system past one or more treatment or analysis stations
    • G01N35/04—Details of the conveyor system
    • G01N2035/0401—Sample carriers, cuvettes or reaction vessels
    • G01N2035/0406—Individual bottles or tubes

Definitions

  • This application relates to the field of blood testing, and in particular to a sample analysis system, a cell image analyzer, a method for automatically detecting platelets, and a computer-readable storage medium.
  • Blood cells are generally classified into three types of cells: red blood cells (RBC), white blood cells (WBC), and platelets (PLT).
  • RBC red blood cells
  • WBC white blood cells
  • PHT platelets
  • Platelet count is an important test item for clinical diagnosis and treatment of thrombocytopenia caused by various reasons. Platelet count refers to the number of platelets contained in a unit volume of blood. When the platelet count is lower than a certain value (for example, 20 ⁇ 10 9 /L), it is generally believed that the patient must undergo platelet transfusion, otherwise the patient will be at risk of fatal bleeding. However, on the other hand, unnecessary blood transfusion will lead to waste of clinical costs and clinical risks caused by blood transfusion, such as ineffective platelet transfusion, post-transfusion purpura, etc. Therefore, accurate count of platelets has very important clinical significance.
  • a certain value for example, 20 ⁇ 10 9 /L
  • blood cell analyzers use impedance or optical methods to count platelets in blood samples.
  • the blood cell analyzer can accurately count platelets, but for abnormal samples (such as platelet aggregation samples), the platelet count results of the blood cell analyzer have relatively large deviations.
  • the laboratory doctor judges that the platelet count result of the liquid cell analyzer is abnormal, he needs to re-examine the blood sample under a microscope to confirm the platelet count value, and rely on human experience to determine whether the platelet is really abnormal. This not only puts forward higher requirements for the laboratory doctor, but also is prone to human error and low efficiency.
  • the embodiments of the present application provide a sample analysis system, a cell image analyzer, a method, and a computer-readable storage medium, which can efficiently and automatically detect platelets in abnormal samples, reducing or even without manual intervention, and improving the efficiency and efficiency of blood testing. accuracy.
  • the first aspect of the application provides a sample analysis system, including:
  • Blood cell analyzer configured to detect cells in blood samples to obtain blood test results
  • Smear preparation device configured to prepare smears for blood samples
  • Cell image analyzer configured for image capture and analysis of cells in the smear
  • the transport device includes a first transport track and a second transport track, the first transport track is configured to transport the blood sample from the blood cell analyzer to the smear preparation device, and the second transport track is configured to transport the smear Transport from the smear preparation device to the cell image analyzer;
  • the control device is in communication connection with the blood cell analyzer, the smear preparation device, the cell image analyzer, and the transport device, and is configured to:
  • the first transmission track is instructed to transport the blood sample to be tested to the smear preparation device, and the smear preparation device is instructed Prepare the test smear of the blood sample to be tested, instruct the second transport track to transport the test smear to the cell image analyzer, and instruct the cell image analyzer to photograph the test smear Slice the cell image and analyze the cell image,
  • the cell image analyzer determines that there is no platelet aggregation in the blood sample to be tested according to the cell image
  • the cell image analyzer estimates the platelet count of the blood sample to be tested according to the cell image.
  • the second aspect of the application provides a sample analysis system, including:
  • Blood cell analyzer configured to detect cells in blood samples to obtain blood test results
  • Smear preparation device configured to prepare smears for blood samples
  • Cell image analyzer configured for image capture and analysis of cells in the smear
  • the transport device includes a first transport track and a second transport track, the first transport track is configured to transport the blood sample from the blood cell analyzer to the smear preparation device, and the second transport track is configured to transport the smear Transport from the smear preparation device to the cell image analyzer;
  • the control device is in communication connection with the blood cell analyzer, the smear preparation device, the cell image analyzer, and the transport device, and is configured to:
  • the first transport track is instructed to transport the blood sample to be tested to the smear preparation device, and the smear preparation device is instructed Prepare the test smear of the blood sample to be tested, instruct the second transport track to transport the test smear to the cell image analyzer, and instruct the cell image analyzer to photograph the test smear Slice of cell image,
  • the cell image analyzer estimates the platelet count of the blood sample to be tested and/or determines whether there is platelet aggregation in the blood sample to be tested according to the cell image.
  • a third aspect of the present application provides a cell image analyzer for analyzing smears, including:
  • a digital imaging device having a plurality of objective lenses and a digital camera, the digital camera being used for taking images of cells in a smear prepared from a blood sample to be tested under the objective lens;
  • a smear moving device for adjusting the relative position of the digital imaging device and the smear
  • the controller includes a memory controlled by the processor, and the memory stores instructions that enable the processor to perform the following operations:
  • the platelet count of the blood sample to be tested is estimated according to the cell image.
  • the fourth aspect of the present application provides a method for automatically detecting platelets, including:
  • the blood cell analyzer obtains the blood test results of the blood sample to be tested
  • the smear preparation device prepares the test smear of the blood sample to be tested, and the cell image analyzer obtains the test smear of the blood sample to be tested.
  • the cell image analyzer determines that there is no platelet aggregation in the blood sample to be tested based on the cell image
  • the cell image analyzer estimates the platelet count of the blood sample to be tested based on the cell image.
  • the fifth aspect of the present application provides a method for automatically detecting platelets, including:
  • the first transport track transports the blood sample to be tested from the blood cell analyzer to the smear preparation device
  • the smear preparation device prepares the smear to be tested of the blood sample to be tested,
  • the second transport track prepares and transports the smear to be tested from the smear preparation device to the cell image analyzer
  • the cell image analyzer captures the cell image of the smear to be tested, and estimates the platelet count of the blood sample to be tested based on the cell image and/or determines whether the blood sample is to be tested based on the cell image There is platelet aggregation.
  • a sixth aspect of the present application provides a computer-readable storage medium, the computer storage medium stores a computer program, and the computer program includes program instructions that, when executed by a processor, cause the processor to execute Apply for the method described in the fourth aspect or the fifth aspect of this application.
  • the blood cell analyzer obtains the blood test result of the blood sample to be tested; in the case that the blood test result of the blood sample to be tested indicates that there is abnormal platelet in the blood sample to be tested, the smear preparation device prepares the test result.
  • the cell image analyzer obtains the cell image of the test smear; the cell image analyzer judges whether there is platelet aggregation in the test blood sample and/or estimates the blood sample’s status based on the cell image Platelet count, or when the cell image analyzer judges that there is no platelet aggregation in the blood sample to be tested according to the cell image, the platelet count of the blood sample to be tested is estimated.
  • the embodiment of the present application can automatically determine whether the blood sample to be tested has platelet abnormality according to the detection result of the blood cell analyzer, and automatically transport the sample to be tested to when it is determined that there is platelet abnormality in the blood sample to be tested
  • the smear preparation device prepares the smear to be tested, and then automatically transports the smear to be tested to the cell image analyzer for image shooting and analysis, so that the cell image analyzer can automatically determine whether there is platelet aggregation in the blood sample to be tested and estimate the Measure the platelet count of the blood sample.
  • the cell image analyzer can accurately estimate the platelet count in the blood sample to be tested. It does not require the examiner to count platelets under the microscope for a long time, which improves the efficiency of platelet counting and reduces the number of platelets. Artificial error.
  • FIG. 1 is a schematic structural diagram of a sample analysis system provided by an embodiment of the present application.
  • FIGS. 2 and 3 are structural perspective views of a smear preparation device provided by an embodiment of the present application from different viewing angles;
  • Fig. 4 is a schematic structural diagram of a cell image analyzer provided by an embodiment of the present application.
  • Fig. 5 is a schematic structural diagram of another cell image analyzer provided by an embodiment of the present application.
  • Figure 6 is a schematic diagram of the structure of a smear provided by an embodiment of the present application.
  • FIG. 7 is a schematic structural diagram of a control device provided by an embodiment of the present application.
  • FIGS. 8 to 12 are schematic flowcharts of a method for automatically detecting platelets according to different embodiments of the present application.
  • FIG. 13 is a schematic flowchart of a method for counting platelets according to an embodiment of the application.
  • Fig. 14 is a gray histogram of a cell image provided by an embodiment of the present application.
  • FIG. 15 is a schematic diagram of a deep neural network structure provided by an embodiment of the present application.
  • FIG. 16 is a schematic structural diagram of a platelet detection device provided by an embodiment of the application.
  • FIG. 17 is a schematic structural diagram of another platelet detection device provided by an embodiment of the present application.
  • FIG. 1 is a schematic structural diagram of a sample analysis system provided by an embodiment of the present application.
  • the sample analysis system 100 includes a blood cell analyzer 110, a smear preparation device 120, a cell image analyzer 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 for preparing smears of the sample to be tested
  • the cell image analyzer 130 is used for image capture and analysis of the cells in the smear
  • the control device 140 is in communication connection with the blood analyzer 110, the smear preparation device 120, and the cell image analyzer 130.
  • the sample analysis system 100 also includes a first transfer track 150 and a second transfer track 160.
  • the first transfer track 150 is used to transport a test tube rack 10 that can hold a plurality of test tubes 11 loaded with samples to be tested from the blood analyzer 110 to the coating.
  • the slide preparation device 120 and the second transport track 150 are used to transport the slide basket 20 that can load a plurality of prepared smears 21 from the smear preparation device 120 to the cell image analyzer 130.
  • the control device 140 is electrically connected to the first transmission track 150 and the second transmission track 160 and controls their actions. In some embodiments, the control device 140 is indirectly electrically connected with the first transmission track 150 and the second transmission track 160 through a dispatch controller (not shown).
  • control device 140 is configured to:
  • Obtain a sample test result of a sample to be tested (for example, a blood sample) from the blood cell analyzer 110;
  • the first transport track 150 is instructed to transport the sample to be tested (in a manner of being loaded in a sample tube) to the smear preparation device 120, indicating The smear preparation device 120 prepares the test smear of the test sample, instructs the second transport track 160 to transport the test smear to the cell image analyzer 130, and instructs the cell image analyzer 130 to take the cell image of the test smear and Estimate the platelet count of the sample to be tested based on the cell image and/or determine whether there is platelet aggregation in the sample to be tested, or the cell image analyzer 130 determines that there is no platelet aggregation in the sample to be tested according to the cell image
  • the cell image estimates the platelet count of the sample to be tested or prompts whether to estimate the platelet count of the sample to be tested based on the cell image.
  • the sample analysis system 100 can efficiently and automatically detect platelets in abnormal samples, reducing manual intervention, even without manual intervention.
  • the cell image analyzer can more accurately estimate the platelet count in the blood sample to be tested.
  • the embodiment of the present application does not require inspectors to count platelets under a microscope for a long time, which improves the efficiency of platelet counting and reduces manual errors at the same time.
  • the blood cell analyzer 110 detects the blood sample 11 to be tested on the test tube rack 10, and obtains the blood test result of the blood sample to be tested (the blood test result may include platelet test results, red blood cell test results, white blood cell test results, etc.).
  • the control device 140 determines according to the blood test result that the blood sample 11 to be tested on the test tube rack 10 needs to be retested (for example, the blood test result of the blood sample to be tested indicates that there is a low platelet abnormality in the blood sample to be tested)
  • the control device 140 instructs the first transport track 150 to transport the test tube rack loaded with the blood sample to be tested to be tested to the smear preparation device 120 so as to prepare the smear 21.
  • the smear preparation device 120 stores the prepared smear 21 in the glass slide basket 20, and transports the glass slide basket 20 containing the smear 21 to the cell image analyzer 130 through the second transfer track 160, so that the cell image analyzer 130 takes a smear cell image and analyzes the taken cell image, and estimates the platelet count of the blood sample to be tested when it is analyzed that there is no platelet aggregation in the blood sample to be tested, or directly estimates the platelet count of the blood sample to be tested.
  • the sample analysis system 100 further includes feeding mechanisms 170 and 180 respectively corresponding to the blood analyzer 110 and the smear preparation device 120, and each feeding mechanism 170 and 180 includes Load buffer areas 171 and 181, feed detection areas 172 and 183, and unload buffer areas 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 to the loading buffer area 171 via the first transfer track 150, and then transported from the loading buffer area 171 to the feeder.
  • the detection area 172 is detected by the blood analyzer 110. After the detection is completed, it is unloaded from the feed detection area 172 to the unloading buffer area 173, and finally from the unloading buffer area 173 into the first transport track 150.
  • the test tube rack 10 needs to be transported to the smear preparation device 120 to prepare a smear of the sample to be tested.
  • 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 feed detection area 182.
  • the smear preparation device 120 prepares the smear of the sample to be tested. After the end, it is unloaded from the feed detection area 182 to the unloading buffer area 183, and finally enters the first transport track 150 from the unloading buffer area 183.
  • the smear preparation device 120 stores the prepared smears in the glass slide basket 20, and transports the glass slide basket 20 containing the smear to be tested to the cell image analyzer 130 through the second transfer track 160.
  • the cell image analyzer 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 the test result of the sample, which can be set on the blood analyzer 110, the cell image analyzer 130, or the control device 140, or separately.
  • the display device may include a display screen, such as a liquid crystal display screen, an OLED display screen, and the like.
  • the display device is configured to display the analysis result of platelet aggregation in the sample to be tested and to display the platelet count of the sample to be tested.
  • the blood cell analyzer 110 is used to perform routine blood tests on a sample to be tested, such as a blood sample, to obtain a sample test result.
  • Blood routine parameters or blood test results can include WBC (white blood cell) five classification results, WBC count and morphological parameters, HGB (hemoglobin, hemoglobin) test results, RBC (red blood cell, red blood cell) and PLT (blood platelet) , Platelet) count and at least one or more combinations of morphological parameters.
  • the blood cell analyzer 110 generally includes a sampling device, a sample preparation device, an optical detection device, and a controller (not shown).
  • the sampling device has a sampling needle for collecting blood samples and transporting the collected blood samples to the sample preparation device.
  • the sample preparation device has a reaction tank and a reagent supply part, and the reagent supply part stores reagents for reacting with the blood sample and supplies corresponding reagents to the reaction tank as needed.
  • the sample preparation device may include at least one reaction cell, wherein the at least one reaction cell may be configured to cause the blood sample from the sampling part and the reagent from the reagent supply part to react to prepare the sample to be tested.
  • the optical detection device includes a light source, a flow chamber, and a light detector.
  • the particles to be tested can flow in the flow chamber, and the light emitted by the light source illuminates the particles in the flow chamber to generate optical information.
  • the optical detector detects the optical information.
  • the controller is used to control the actions of the sampling device, the sample preparation device, and the optical detection device, and is used to obtain the optical information measured by the optical detection device, so as to further obtain the blood routine detection result of the blood sample.
  • the blood cell analyzer 110 also includes an impedance detection device (not shown).
  • the impedance detection device includes a flow chamber with a hole with an electrode.
  • the impedance detection device detects the DC impedance generated when the particles in the sample to be tested pass through the hole, and outputs an electrical signal reflecting the information when the particles pass through the hole. It is understandable that the blood cell analyzer 110 can detect platelets in the blood sample to be tested through its impedance detection device (ie, impedance method) or optical detection device (ie, optical method) to obtain platelet impedance method detection results or platelet optical method detection. result.
  • impedance detection device ie, impedance method
  • optical detection device ie, optical method
  • the blood cell analyzer 110 can also detect the platelets in the blood sample to be tested through its impedance detection device and optical detection device to obtain the platelet impedance method detection result and the platelet optical method detection result.
  • the optical detection device of the blood cell analyzer 110 can be used to detect the platelets in the blood sample to be tested.
  • the impedance detection device and the optical detection device of the blood cell analyzer 110 can also be used to detect platelets in the blood sample to be tested.
  • the blood cell analyzer 110 communicates with the control device 140 through its controller, so as to transmit the sample detection result to the control device 140, or can also receive information from the control device 140.
  • FIGS. 2 and 3 show schematic structural diagrams of the smear preparation device 120, which can be used for preparation of smears for blood, body fluids and other samples.
  • the smear preparation device 120 includes a sampling mechanism 121 for drawing a sample, a slide loading mechanism 122 for moving the slide to the work line, a sample loading mechanism 123 for loading the sample on the slide, and a sample loading mechanism 123 for loading the sample on the slide.
  • the slide pushing mechanism 124 for smoothing the sample on the slide, the drying mechanism (not shown in the figure) for drying the blood film on the slide, and the staining mechanism 125 for staining the slide.
  • the smear preparation device 120 also includes a controller (not shown) configured to control the operations of the various mechanisms of the smear preparation device 120.
  • the smear preparation device 120 communicates with the control device 140 through its controller, so as to receive a push instruction from the control device 140 or send data to the control device 140.
  • the controller of the smear preparation device 120 may also directly communicate with the controller of the blood cell analyzer 110, so as to obtain the sample analysis result of the sample to be tested from the blood cell analyzer 110, so as to determine whether it needs to be treated. Push the test sample.
  • the controller controls the sampling mechanism 121 to perform sample extraction.
  • the sampling device in the sampling mechanism 121 such as the sampling needle 1211, is used to aspirate the sample and pass
  • the unshown pipeline transports the sample extracted by the sampling mechanism 121 to the sample adding mechanism 123; controls the slide loading mechanism 122 to extract blank slides and load the blank slides to the working position to facilitate the blood dripping operation; control
  • the sample adding mechanism 123 drops the sample onto the blank glass slide in the working position; the slide pushing mechanism 124 is controlled to push the sample on the blank glass slide into a sample film shape.
  • the controller of the smear preparation device 120 can also control the drying mechanism to dry the sample film on the glass slide to stabilize its shape; and can also control the dyeing mechanism 125 to dye the sample film on the glass slide.
  • the smear preparation device 120 of the embodiment of the present application can execute an automatic smear preparation procedure, realize automatic preparation of smears, and improve the efficiency of blood smear preparation.
  • the cell image analyzer 130 may also be referred to as a scanning machine, a digital cell image analysis system, or a digital microscope.
  • the cell image analyzer 130 includes an imaging device 131, a smear moving device 132, and a controller 133.
  • the imaging device 131 includes a camera 1312 and a lens group 1311 and is used to perform cell analysis on the samples 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 captures a cell image of a specific area of the smear.
  • the lens group 1311 may include a first objective lens and a second objective lens.
  • the first objective lens may be, for example, a 10 times objective lens
  • the second objective lens may be, for example, a 100 times 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 further include eyepieces, for example.
  • the cell image analyzer 130 also includes an identification device 134, a slide clamping 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 tested Smear.
  • the cell image analyzer 130 also includes a slide basket loading device 137 for loading a slide basket containing the smear to be tested, and the slide gripping 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 second transport track 160 so that the smear prepared by the smear preparation device 120 can be transported to the cell image analyzer 130.
  • the controller 133 of the cell image analyzer 130 is used to control the actions of the imaging device 131, the smear moving device 132, the recognition device 134, and/or the slide gripping device 135, etc., and to analyze the cell image of the smear.
  • the cell image analyzer 130 communicates with the control device 140 through its controller, so that it can receive instructions from the control device 140 for image capture and analysis of the smear to be tested, or transmit the detection data of the cell image analyzer 130 to the control device. ⁇ 140 ⁇ Device 140.
  • the controller 133 of the cell image analyzer 130 may also directly communicate with the smear preparation device 120 and/or the controller of the blood cell analyzer 110 to obtain shooting instructions.
  • the controller 133 of the cell image analyzer 130 is configured to:
  • Control the smear moving device 132 to adjust the smear prepared from the sample to be tested to a predetermined position
  • the platelet count of the sample to be tested is estimated based on the cell image or a prompt is made whether to estimate the platelet count of the blood sample to be tested based on the cell image.
  • the cell image analyzer 130 is further configured to capture a cell image of a specific region of the smear prepared from the sample to be tested when platelet abnormalities exist in the sample to be tested, and the specific region includes the sample to be tested. At least one of the body-tail junction area, the edge area on both sides, and the tail area of the smear.
  • the smear includes a label area and a blood film area. Sample identification information or other marking information is printed on the label area, and the sample to be tested is smeared on the blood film area. The sample is applied to the blood film area from the head of the blood film area to the tail of the blood film area. Usually, platelet aggregation is more likely to be found in the marginal areas on both sides of the blood membrane.
  • the cell image analyzer 130 is further configured to determine the shape of the platelets in the sample to be tested based on the cell image of the smear prepared from the sample to be tested when there is an abnormality of platelets in the sample to be tested Whether it is abnormal.
  • the control device 140 at least includes: a processing component 141, a random access memory (RAM) 142, a read-only memory (ROM) 143, and a communication interface 144, a memory 146 and an I/O interface 145, wherein the processing component 141, RAM 142, ROM 143, communication interface 144, memory 146 and I/O interface 145 communicate through a bus 147.
  • RAM random access memory
  • ROM read-only memory
  • I/O interface 145 I/O interface 145
  • the processing component may be a central processing unit (CPU), a graphics processing unit (GPU), or other chips with computing capabilities.
  • CPU central processing unit
  • GPU graphics processing unit
  • the memory 146 is loaded with various computer programs such as an operating system and application programs for the processor component 141 to execute, and data required to execute the computer programs. In addition, during the sample detection process, any data that needs to be stored locally can be stored in the memory 146.
  • the input/output (I/O) interface 146 is composed of, for example, universal serial bus (universal serial bus, USB), institute of electrical and electronics engineers (IEEE) 1394 or recommended standards (recommended standards). standard) RS-232C and other serial interfaces, small computer system interface (SCSI), integrated drive electronics (IDE) interface, or IEEE1284 parallel interface, as well as digital/analog (digital/analog, D /A) converter and analog/digital (analog/digital, A/D) converter and other components of the analog signal interface composition.
  • An input device composed of a keyboard, a mouse, a touch screen or other control buttons is connected to the I/O interface 145, and the user can use the input device to directly input data to the control device 140.
  • the I/O interface 145 can also be connected to a display with display function, such as: LCD screen, touch screen, LED display screen, etc.
  • the control device 140 can output the processed data as image display data to the display for display, for example : Analyze data, instrument operating parameters, etc.
  • the communication interface 144 is an interface that can be any currently known communication protocol.
  • the communication interface 144 communicates with the outside world through the network.
  • the control device 140 can transmit data with any device connected through the network through the communication interface 144 using a certain communication protocol.
  • the controllers of the blood cell analyzer 110, the smear preparation device 120, and the cell image analyzer may also have a structure similar to the control device 140, which will not be repeated here.
  • control device 140 may be independent of the controller of the blood cell analyzer 110, the smear preparation device 120, and the cell image analyzer, or may be integrated into the blood cell analyzer 110, the smear preparation device 120.
  • one of the controllers of the cell image analyzer may also include the above-mentioned blood cell analyzer 110, the smear preparation device 120, and the controller of the cell image analyzer.
  • the following describes the method for automatically detecting platelets provided in the embodiments of the present application.
  • the method provided in the embodiment of the present application can be applied to the above-mentioned sample analysis system 100, and in particular can be implemented by the control device 140.
  • FIG. 8 is a schematic flowchart of a method for automatically detecting platelets according to an embodiment of the present application. The method includes the following steps:
  • the blood cell analyzer 110 obtains the sample test result of the sample to be tested
  • the smear preparation device 120 prepares a test smear of the sample to be tested;
  • the cell image analyzer 130 acquires a cell image of the smear to be tested, and judges whether there is platelet aggregation in the sample to be tested based on the cell image, and/or estimates the platelet count in the sample to be tested.
  • the control device 140 establishes a communication connection with the blood cell analyzer 110, the smear preparation device 120, and the cell image analyzer 130, respectively.
  • the process steps of the above method for automatically detecting platelets are specifically as follows: After the blood cell analyzer 110 obtains the blood test result of the sample to be tested, for example, the blood sample to be tested, the blood test result is sent to the control device 140, and the control device 140 uses the blood When the detection result determines that there is a platelet abnormality in the sample to be tested, the control device 140 sends a smear preparation instruction to the smear preparation device 120 and a smear shooting and analysis instruction to the cell image analyzer 130, so that the smear preparation device 120 automatically prepares the smear preparation device 120.
  • the test smear of the sample to be tested and the cell image analyzer 130 acquire and analyze the cell image of the test smear.
  • the cell image analyzer 130 then automatically determines whether there is platelet aggregation in the blood sample to be tested based on the cell image, or estimates the platelet count of the blood sample to be tested based on the cell image, or determines whether there is platelet aggregation in the blood sample to be tested based on the cell image and estimates The platelet count of the blood sample to be tested or a prompt whether to estimate the platelet count of the blood sample to be tested based on the cell image.
  • control device 140 is integrated in one of the blood cell analyzer, the smear preparation device, and the cell image analyzer.
  • the control device 140 is integrated in a blood cell analyzer, and the blood cell analyzer establishes a communication connection with the smear preparation device and the cell image analyzer, respectively.
  • the process steps of the above method for automatically detecting platelets are specifically as follows: after the blood cell analyzer 110 obtains the blood test result of the blood sample to be tested, if it is determined that there is abnormal platelet in the blood sample to be tested according to the blood test result, the blood cell analyzer 110 Send the smear preparation 120 instructions to the smear preparation device and the smear shooting and analysis instructions to the cell image analyzer 130, so that the smear preparation device 120 automatically prepares the test smear of the sample to be tested and the cell image analyzer 130 Obtain and analyze the cell image of the smear to be tested. The cell image analyzer 130 then automatically determines whether there is platelet aggregation in the blood sample to be tested based on the cell image and/or estimates the platelet count in the blood sample to be tested based on the cell image.
  • the detection of the sample to be tested by the blood analysis system can be ended, or the sample to be tested can be transported to other analyzers in the sample analysis system for detection and analysis.
  • FIG. 9 is a schematic flowchart of a method for automatically detecting platelets according to an embodiment of the present application. The method includes the following steps:
  • the blood cell analyzer 110 obtains the sample test result of the sample to be tested
  • the smear preparation device 120 prepares a test smear of the sample to be tested;
  • the cell image analyzer 130 acquires a cell image of the smear to be tested.
  • the cell image analyzer 130 determines that there is no platelet aggregation in the sample to be tested according to the cell image, the cell image analyzer 130 estimates the platelet count of the sample to be tested according to the cell image or prompts whether to The cell image estimates the platelet count of the blood sample to be tested.
  • the cell image analyzer 130 when the cell image analyzer 130 determines that there is no platelet aggregation in the sample to be tested according to the cell image, the cell image analyzer 130 further estimates the platelet count in the sample to be tested based on the cell image.
  • the cell image analyzer 130 can automatically estimate the platelet count in the sample to be tested, and can also semi-automatically estimate the platelet count in the sample to be tested according to the manual count value of the user.
  • the cell image analyzer 130 may also prompt that there is no platelet aggregation in the sample to be tested and prompt the user to select the sample to be tested for counting. Further, the cell image analyzer 130 may output a prompt that the user can select manual counting or automatic counting. When the user selects automatic counting, the cell image analyzer 130 automatically estimates the platelet count in the sample to be tested based on the cell image. When the user selects manual counting, the cell image analyzer 130 prompts the user to input the manual count value after receiving the manual counting instruction, so that the cell image analyzer 130 can further estimate the platelet count in the sample to be tested. The specific method of counting platelets will be described in detail below.
  • the method shown in FIG. 9 further includes step 905, when the cell image analyzer 130 determines that there is platelet aggregation in the sample to be tested according to the cell image, outputting a prompt that there is platelet aggregation in the sample to be tested. Further, in this case, a prompt for platelet re-examination of the new test sample of the same subject is also output, that is, the new test sample of the same subject is reacquired, and the new test sample is re-examined.
  • the sample is transported to the blood cell analyzer 110 for re-examination, or transported to the smear preparation device 120 to prepare a new smear to be tested, and then transported to the cell image analyzer 130 for image capture and analysis.
  • FIG. 10 is a schematic flowchart of a method for automatically detecting platelets according to an embodiment of the present application. The method includes the following steps:
  • the blood cell analyzer 110 obtains a sample test result of the sample to be tested.
  • step 1002 is executed;
  • the first transport track 150 transports the sample to be tested from the blood cell analyzer 110 to the smear preparation device 120,
  • the smear preparation device 120 prepares the test smear of the test sample
  • the second transport track 160 prepares and transports the smear to be tested from the smear preparation device 120 to the cell image analyzer 130,
  • the cell image analyzer 130 takes a cell image of the smear to be tested, and estimates the platelet count in the sample to be tested based on the cell image and/or judges whether the sample to be tested is in the sample based on the cell image There is platelet aggregation.
  • the test result of the blood cell analyzer 110 of the sample to be tested includes at least one of a platelet test result and a red blood cell test result
  • the platelet test result includes the test sample passed through the blood cell At least one of platelet count or platelet concentration, platelet histogram, platelet scatter diagram, platelet aggregation prompt, platelet size detected by the analyzer 110
  • the red blood cell detection result includes that the sample to be tested is passed through the blood cell analyzer 110 At least one of a small red blood cell test result and a red blood cell fragment test result is detected.
  • platelet abnormalities include low platelet count values, high platelet count values, abnormal platelet histograms/scatter plots, platelet aggregation, the presence of a certain number of huge platelets, the presence of a certain number of small red blood cells, and the presence of a certain number of small red blood cells.
  • Small red blood cells refer to smaller red blood cells (7-9um) in diameter than normal red blood cells.
  • Giant platelets refer to platelets with a diameter greater than 7um, large platelets are platelets with a diameter equal to 3 to 6um, and normal platelets have a diameter of 1 to 3um. Therefore, small red blood cells may interfere with the platelet count, resulting in high platelets, and huge platelets may cause low counts.
  • Blood cell counting instruments usually use the impedance method to count platelets.
  • the small red blood cells and red blood cell fragments are similar in size to platelets, it is easy to mistake the small red blood cells and red blood cell fragments as platelets. Platelet falseness is too high, causing false clinical diagnosis.
  • the large platelets and red blood cells are similar in size, so it is easy to mistake the large platelets as red blood cells, resulting in inaccurate platelet counts.
  • platelet aggregation is also likely to cause low platelet falsehood, which affects clinical judgment.
  • the platelet count detected by the blood cell analyzer 110 exceeds the preset value interval, and the blood analyzer 110 prompts that the sample to be tested is in the sample There is platelet aggregation, the blood cell analyzer 110 detects a certain number of giant platelets in the sample to be tested, the blood cell analyzer 110 detects a certain number of small red blood cells in the sample to be tested, and the blood cell analyzer 110 detects the sample to be tested There is a certain amount of red blood cell fragments in it.
  • the platelet count exceeds the preset numerical interval, which means that the platelet count is not within the preset numerical interval.
  • the preset value range is 100 ⁇ 10 9 to 1000 ⁇ 10 9 , if the number of platelets in the blood sample to be tested is less than 100 ⁇ 10 9 or greater than 1000 ⁇ 10 9 , it is considered that there is a platelet abnormality.
  • the blood cell analyzer 110 uses the impedance method or the optical method to detect the sample to be tested to obtain the sample detection result.
  • the impedance method distinguishes platelets based on the difference between platelet volume and red blood cell volume.
  • the impedance method has a large deviation.
  • the optical method distinguishes platelets and erythrocytes based on the intensity of scattered light and/or the intensity of fluorescence generated when the platelets and red blood cells are irradiated with light. It is generally believed that the optical method is more accurate than the impedance method, but the cost of the optical method is higher than that of the impedance method.
  • some blood cell analyzers may not be equipped with optical devices, and optical methods cannot be used for detection.
  • the optical method may be used to detect the sample to be tested under the condition of priority to accuracy, and the impedance method can be used to detect the sample to be tested under the condition of priority to cost.
  • the blood cell analyzer 110 uses the impedance method and the optical method to detect the sample to be tested to obtain the sample detection result.
  • the optical method is more accurate than the impedance method.
  • the accuracy of the optical method may be lower. It may be lower than the impedance method. Therefore, the embodiment of the present application adopts two simultaneous detection methods. If the detection results of the two methods are not abnormal, the detection result is determined to be normal. If the result of any of the detection methods is abnormal, it is determined that the detection result is abnormal. The embodiments of the present application can improve the detection reliability of the sample detection result.
  • the steps of the blood cell analyzer 120 obtaining the sample test result of the sample to be tested include:
  • the blood cell analyzer 110 uses the impedance method to detect the sample to be tested to obtain the platelet impedance method detection result;
  • the blood cell analyzer 110 uses an optical method to detect the sample to be tested to obtain a platelet optical method detection result, wherein the sample
  • the detection result includes the detection result of the platelet impedance method and the detection result of the platelet optical method.
  • the impedance method is first used for detection. If the detection result of the impedance method is abnormal, the optical method is further used for detection.
  • the embodiment of the present application can take into account the detection cost and detection accuracy in the detection process of the blood sample to be tested by the blood cell analyzer.
  • steps 1103 and 1104 of the method shown in FIG. 11 reference may be made to steps 802 and 803 of the method shown in FIG. 8, which will not be repeated here.
  • the method further includes: the cell image analyzer 130 determines whether the shape of the platelets in the sample to be tested is abnormal according to the cell image.
  • the morphological abnormalities of platelets may include: large platelets and giant platelets.
  • Large platelets are platelets with a diameter equal to 3-6um, and giant platelets refer to platelets with a diameter greater than 7um. If the ratio of large platelets (the ratio of large platelets refers to the ratio of large platelets to the total platelets) is high, it may be that the mechanism of platelets forming small platelets is impaired and the maturity is reduced, which can be seen in essential thrombocythemia. If the ratio of large platelets is low, the platelet maturity is high. If there are giant platelets, it may be due to platelet membrane defects that cause giant platelet syndrome.
  • the method further includes: outputting an analysis result of whether there is platelet aggregation in the sample to be tested and/or outputting the platelet count of the sample to be tested.
  • the analysis result of platelet aggregation includes the platelet aggregation analysis result of the cell image analyzer 130 on the sample to be tested, and further includes the platelet aggregation analysis result of the blood cell analyzer 110 on the sample to be tested; the platelet count includes cell image analysis.
  • the meter 130 counts the platelets of the sample to be tested, and further includes the blood cell analyzer 110 counts the platelets of the sample to be tested.
  • the embodiment of the present application also provides another method for detecting platelets. As shown in FIG. 12, the method includes the following steps:
  • the platelet count in the sample to be tested can be directly estimated based on the cell image.
  • the cell image analyzer 130 can automatically estimate the platelet count based on the platelet aggregation result, or can estimate the platelet count in response to user instructions after prompting the user.
  • the steps of the cell image analyzer 130 to estimate the platelet count in the sample to be tested according to the cell image include:
  • the ratio of the number of platelets in the cell image to the number of reference cells can be obtained , Multiply the ratio of the number of platelets in the cell image to the number of reference cells by the reference cell count of the sample to be tested to estimate the platelet count of the sample to be tested.
  • the platelet count of the sample to be tested can be estimated by the following formula:
  • N PLT is the platelet count to be estimated
  • N RFBC is the reference cell count of the test sample detected by the blood cell analyzer 110
  • M PLT is the number of platelets in the cell image
  • M RFBC is the reference cell number in the cell image.
  • the cell image analyzer 130 may continue to obtain cell images of other areas of the smear to be tested, so as to increase the statistical quantity, thereby more accurately according to the cell Image to estimate the platelet count in the sample to be tested.
  • an image segmentation method or a deep learning method is used to identify platelets and reference cells in the cell image.
  • step 1301 includes: recognizing the cell area in the cell image based on the feature difference between the cell and the background in the cell image; and comparing the cell area in the cell area based on the feature difference of different cells
  • the classification is performed to identify the platelet area and the reference cell area in the cell area; accordingly, step 1302 includes: counting the number of platelets in the platelet area and the number of reference cells in the reference cell area.
  • the characteristic difference between the cell and the background in the cell image may include a grayscale difference and a difference in a specific color space component.
  • the cell area and background area in the cell image can be determined according to the gray histogram of the cell image.
  • a cell image analyzer can obtain a grayscale histogram of a cell image, and identify the cell area in the cell image based on the grayscale difference between the cell area and the background area in the grayscale histogram.
  • FIG. 14 is a gray histogram of a cell image disclosed in an embodiment of the present application.
  • the abscissa of the grayscale histogram is the gray value of the pixel point of the cell image
  • the ordinate is the number of pixel points corresponding to the gray value.
  • the gray value of the cell area is between 100-200
  • the gray value of the background is between 200-255.
  • the cell image analyzer can determine the area where the gray value of the pixel point of the cell image is between 100-200 as the cell area, and the area where the gray value of the pixel point of the cell image is between 200-255 as the background area .
  • the cell image analyzer can be based on an image segmentation method based on edge detection. According to the obvious difference in color and brightness between the cells and the background, that is, there is a more obvious edge, the edge of the cell can be detected by using the gradient. To achieve the separation of cells and background.
  • the specific color space includes red green blue (RGB) color space, hue saturation value (HSV) color space, hue saturation intensity (HSI) color One of space, Lab color space, luminance chrominance (YUV) color space, luminance chrominance blue chrominance (luminance chrominance blue chrominance red) YCbCr color space.
  • the components of a specific color space include any component in the RGB color space or any component in the HSV color space or any component in the HSI color space or any component in the Lab color space or any component in the YUV color space or in the YCbCr color space Any component.
  • the cell image analyzer can identify red blood cells and platelets based on the difference in the S component of the cell image in the HSI color space.
  • the S component of platelets and nucleated cells such as white blood cells
  • the S component of red blood cells is generally between 0-150, which can be based on the size of the S component in the cell image
  • the cell image analyzer then distinguishes the platelet area and the white blood cell area according to the size of the connected area in the first area.
  • the connected area includes eight connected areas or four connected areas.
  • the eight-connected area refers to a combination of movement in eight directions starting from each pixel in the area, namely, up, down, left, right, upper left, upper right, lower left, and lower right. Under the premise of the area, reach any pixel in the area.
  • the four-connected area means that starting from each pixel in the area, it can pass through four directions, namely, the combination of the four directions of up, down, left and right, and reach the area within the area without going out of the area. Any pixel.
  • the diameter of leukocyte nuclei is larger than that of platelets.
  • the cell image analyzer can distinguish white blood cells and platelets based on the cell size of white blood cell nuclei and platelets.
  • the cell image analyzer uses one of the support vector machine method, artificial neural network method or Bayesian method to classify the cells in the cell area based on the difference in characteristics of different cells, and identify the cell area Platelet area and reference cell area in the middle.
  • the reference cell is an red blood cell as an example.
  • the cell image analyzer 130 can count the number of single connected areas in the red blood cell area to obtain the number of red blood cells in the cell image.
  • the cell image analyzer 130 counts the number of platelet-connected areas in the platelet area to obtain the number of platelets in the cell image in the specified area.
  • the singly connected region is defined as follows: Let D be a region, and if the interior of any simple closed curve in D belongs to D, then D is called a singly connected region.
  • the singly connected region can also be described as follows: The area enclosed by any closed curve in D contains only the points in D. More generally speaking, a simply connected area is an area without "holes".
  • the definition of a multi-connected region is as follows: Let D be a region, if there is a simple closed curve in D, and the inside of the simple closed curve does not belong to D, then D is called a multi-connected region. More generally speaking, a multi-connected area is an area with "holes".
  • the cell image analyzer 130 counts the number of platelets in the platelet area and counts the number of red blood cells in the red blood cell area; if the reference cells include white blood cells, the cell image analyzer 130 counts the number of platelets in the platelet area. Count the number of white blood cells in the white blood cell area; if the reference cells include a combination of red blood cells and white blood cells, the cell image analyzer 130 counts the number of platelets in the platelet area, the number of red blood cells in the red blood cell area, and the number of white blood cells in the white blood cell area.
  • the cell image analyzer 130 counts the number of platelets in the platelet area, which may specifically include the following steps:
  • the number of connected areas in the platelet area is counted, and the number of connected areas in the platelet area is taken as the number of platelets in the platelet area.
  • the cell image analyzer 130 counts the number of reference cells in the reference cell area, which may specifically include the following steps:
  • the reference cells include red blood cells, filling the multi-connected areas in the red blood cell area to form a single connected area, and determining the number of reference cells in the reference cell area according to the parameters of the single connected area in the red blood cell area;
  • reference cells include white blood cells, counting the number of connected areas in the white blood cell area, and using the number of connected areas in the white blood cell area as the number of reference cells in the reference cell area;
  • the reference cell includes a combination of red blood cells and white blood cells
  • the number of connected areas in the white blood cell area is counted, and the number of white blood cells in the reference cell area is determined according to the number of connected areas in the white blood cell area;
  • the medium and multi-connected areas are filled with holes to form a single-connected area, the number of red blood cells in the reference cell area is determined according to the parameters of the single-connected area in the red blood cell area; the number of white blood cells in the reference cell area is compared with the reference
  • the sum of the number of red blood cells in the cell area is used as the number of reference cells in the reference cell area, or the number of white blood cells in the reference cell area and the number of red blood cells in the reference cell area are respectively used as the number of red blood cells in the reference cell area. Refer to the number of cells.
  • the parameter of the single connected area includes the number of the single connected area; the cell image analyzer determines the number of reference cells in the reference cell area according to the parameter of the single connected area in the red blood cell area, include:
  • the cell image analyzer determining the number of red blood cells in the reference cell area according to the parameters of the single connected area in the red blood cell area includes:
  • the number of single connected areas in the red blood cell area is counted, and the number of single connected areas in the red blood cell area is taken as the number of red blood cells in the reference cell area.
  • the embodiments of this application can be applied to the case where there are no other impurities in the red blood cell area (for example, white blood cell cytoplasm, platelet transparent area). It only needs to count the number of single connected areas in the red blood cell area to accurately count the red blood cells in the reference cell area. Quantity.
  • the parameter of the single connected area includes the number of the single connected area and the area of the single connected area; the cell image analyzer determines the reference according to the parameter of the single connected area in the red blood cell area The number of reference cells in the cell area, including:
  • the cell image analyzer determining the number of red blood cells in the reference cell area according to the parameters of the single connected area in the red blood cell area includes:
  • the area of the single connected domain formed by the cytoplasm of white blood cells is larger than the single connected domain formed by red blood cells, and the area of the single connected domain formed by the transparent area of platelets is smaller than the single connected domain formed by red blood cells.
  • a preset area threshold interval can be set so that the area of a single connected domain formed by red blood cells falls within the set preset area threshold interval, so that the area of a single connected domain formed by the cytoplasm of white blood cells does not fall within the set preset area threshold Within the interval, the area of the single connected domain formed by the platelet transparent area will not fall within the preset area threshold interval.
  • the cell image analyzer counts the number of red blood cells in the red blood cell area, counts the number of white blood cells in the white blood cell area, and takes the number of red blood cells in the red blood cell area as the first
  • the number of reference cells is the number of white blood cells in the white blood cell area as the second reference cell number.
  • the cell image analyzer obtains the number of reference cells in the sample to be tested, based on the number of platelets in the cell image, the number of first reference cells, the number of second reference cells, the first reference cell count of the sample to be tested obtained by the blood cell analyzer 110, The second reference cell count estimates the platelet count of the sample to be tested.
  • the platelet count of the sample to be tested can be estimated according to the following formula:
  • N PLT is the platelet count to be estimated
  • N RBC is the first reference cell (for example, red blood cell) count detected by the blood cell analyzer 110 for the test sample
  • N WBC is the first reference cell (for example, red blood cell) count detected by the hematology analyzer 110 for the test sample.
  • Count of reference cells such as white blood cells
  • M PLT is the number of platelets in the cell image
  • M RBC is the number of reference cells in the cell image
  • M WBC is the number of reference cells in the cell image.
  • 0 ⁇ a ⁇ 1, 0 ⁇ b ⁇ 1, a>b, a+b 1. Since the number of red blood cells in the blood is much greater than the number of white blood cells, the error of red blood cell statistics is relatively small. Consider increasing the weighting coefficient when using red blood cells as reference cells, and reducing the weighting coefficient when using white blood cells as reference cells to further improve Calculation accuracy of platelet count.
  • the platelet count of the sample to be tested can be estimated according to the following formula:
  • N PLT is the platelet count to be estimated
  • N RBC is the first reference cell (for example, red blood cell) count detected by the blood cell analyzer 110 for the test sample
  • N WBC is the first reference cell (for example, red blood cell) count detected by the hematology analyzer 110 for the test sample.
  • Count of reference cells such as white blood cells
  • M PLT is the number of platelets in the cell image
  • M RBC is the number of reference cells in the cell image
  • M WBC is the number of reference cells in the cell image.
  • step 1301 includes: recognizing platelets and reference cells in the cell image through a trained cell type recognition model.
  • the cell type recognition model is a deep neural network model
  • the trained cell type recognition model is a cell type recognition model that meets the requirements obtained through deep learning network training, and is used to recognize platelets and reference cells in cell images. And count the number of platelets and the number of reference cells in the cell image.
  • the detection of the number of platelets and red blood cells in the embodiments of this application can be automatically identified and counted using a deep neural network.
  • deep neural networks contain multiple hidden layers, which use a large number of samples to automatically learn and discover distributed feature representations of data.
  • the advantage of using a deep neural network is that it does not need to manually extract classification features, automatically learn and mine data features, and can obtain higher recognition accuracy.
  • the trained cell type recognition model is obtained by training the cell type recognition model through the training data set.
  • the training data set includes cell pictures used for training, and the cell pictures used for training include labeled platelets and labeled reference cells.
  • the reference cells can be red blood cells, white blood cells, or red blood cells and white blood cells.
  • the deep neural network model may use a fast region convolutional neural network (faster region convolutional neural networks, Faster R-CNN) network, as shown in FIG. 15.
  • the network includes 13 convolutional layers, 4 pooling layers, 1 region of interest (ROI) pooling layer, 1 region proposal network (RPN), 4 fully connected layers, 1 A linear regression layer and a softmax classification layer.
  • ROI region of interest
  • RPN region proposal network
  • multiple convolutional layers and pooling layers are used to automatically generate feature maps; then the recommended candidate regions, that is, the detected cell regions, are generated through the RPN network; the information of these regions is passed to the ROI pooling layer, Reduce each area to the same size; then transfer the same size area information to the fully connected layer, and finally use the softmax classification layer to judge the cell types of these areas; at the same time, use the linear regression layer to correct the cells in the area s position.
  • the network model can also be modified, such as increasing the number of convolutional layers and pooling layers, that is, increasing the network depth.
  • Other regional convolutional neural networks (R-CNN) models such as R-CNN, Fast R-CNN, Mask R-CNN, can also be used. You only need to look at it (You only look once).
  • YOLO YOLO model and target detection (Single Shot MultiBox Detector, SSD) model.
  • Deep neural networks require a large number of labeled samples for network training, and its purpose is to optimize the weights of each neuron in the network to achieve the best network performance.
  • the training of the network can use the gradient descent method. According to the error between the predicted output of the current network and the actual result, the weights of all neurons are continuously adjusted, and finally the error between the predicted output of the network and the actual result is minimized.
  • the step of the cell image analyzer 130 estimating the platelet count in the sample to be tested according to the cell image includes:
  • the platelet count of the sample to be tested is estimated.
  • the predetermined coefficient may be a constant value pre-stored in the storage medium of the controller of the cell image analyzer 130.
  • the predetermined coefficient can be determined based on experience, for example.
  • the predetermined coefficient may be defined by the user, and then input into the cell image analyzer 130.
  • the reference cell may be at least one of white blood cells and red blood cells, and preferably includes at least red blood cells.
  • the user recognizes and counts the platelets of the sample to be tested according to the cell image, and then inputs the count value into the cell image analyzer 130.
  • the cell image analyzer 130 performs the following steps:
  • the platelet count of the sample to be tested is estimated.
  • the cell image analyzer 130 performs the following steps:
  • the platelet count of the sample to be tested is estimated.
  • the platelet detection device 1600 may include a first detection unit 1601, an image acquisition unit 1602, a second detection unit 1603, and an estimation unit 1604.
  • the first detection unit 1601 is configured to obtain the sample detection result of the sample to be tested by the blood cell analyzer and determine whether there is platelet abnormality in the sample to be tested according to the sample detection result.
  • the image acquisition unit 1602 is configured to acquire a cell image of the test smear prepared from the test sample when the first detection unit 1601 determines that there is a platelet abnormality in the test sample.
  • the second detection unit 1603 is configured to determine whether there is platelet aggregation in the sample to be tested according to the cell image.
  • the estimation unit 1604 is configured to estimate the platelet count of the sample to be tested according to the cell image or prompt whether to estimate the platelet count based on the cell image when the second detection unit 1603 determines that there is no platelet aggregation in the sample to be tested. Test the platelet count of the sample.
  • the embodiment of the present application may divide the platelet detection device into functional units according to the foregoing method examples.
  • each functional unit may be divided corresponding to each function, or two or more functions may be integrated into one processing unit.
  • the above-mentioned integrated unit can be implemented in the form of hardware or software functional unit. It should be noted that the division of units in the embodiments of the present application is illustrative, and is only a logical function division, and there may be other division methods in actual implementation.
  • the platelet detection device 1700 includes a processor 1701, a memory 1702, and a communication interface 1703.
  • the processor 1701, the memory 1702, and the communication interface 1703 can communicate with each other.
  • the buses 1704 are connected to each other.
  • the memory 1702 is used to store a computer program
  • the computer program includes program instructions
  • the processor 1701 is configured to call the program instructions to execute part or all of any platelet detection method described in the above embodiments step.
  • An embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program enables a computer to execute part or all of any of the platelet detection methods described in the above embodiments step.
  • the embodiments of the present application also provide a computer program product.
  • the computer program product includes a non-transitory computer-readable storage medium storing a computer program.
  • the computer program enables a computer to execute any of the platelet detection methods described in the above-mentioned embodiments. Some or all of the steps.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.
  • each functional unit in each embodiment may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit.
  • the above-mentioned integrated unit can be implemented in the form of hardware or in the form of software program modules.
  • the integrated unit is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer readable memory.
  • the technical solution of the present application essentially or the part that contributes to the existing technology or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory.
  • a number of instructions are included to enable a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application.
  • the aforementioned memory includes: U disk, read-only memory (read-only memory, ROM), random access memory (random access memory, RAM), mobile hard disk, magnetic disk, or optical disk and other media that can store program codes.
  • the program can be stored in a computer-readable memory, and the memory can include: a flash disk , Read-only memory, random access device, magnetic or optical disk, etc.

Landscapes

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

Abstract

一种样本分析系统(100)及细胞图像分析仪(130)、血小板检测方法及存储介质(1702)，其中，控制装置(140)与血液细胞分析仪(110)、涂片制备装置(120)、细胞图像分析仪(130)和运送装置通信连接，并配置用于：从血液细胞分析仪(110)获取待测样本的样本检测结果(801)；当根据样本检测结果判断待测样本中存在血小板异常时，指示运送装置的第一传输轨道(150)将待测样本运送至涂片制备装置(120)以制备待测血液样本的待测涂片(21)(802)，并指示运送装置的第二传输轨道(160)将待测涂片(21)运送至细胞图像分析仪(130)以拍摄待测涂片(21)的细胞图像；细胞图像分析仪(130)根据细胞图像判断待测样本中是否存在血小板聚集和/或估计待测样本的血小板计数(803)。由此能够高效且自动化地检测异常样本中的血小板，减少人工介入，从而减少人为错误。

Description

样本分析系统及方法、细胞图像分析仪及存储介质 技术领域
本申请涉及血液检测领域，具体涉及一种样本分析系统、细胞图像分析仪、自动检测血小板的方法及计算机可读存储介质。
背景技术
血细胞一般分为红细胞(red blood cell，RBC)、白细胞(white blood cell，WBC)、血小板(platelet，PLT)等三类细胞。
血小板计数是临床诊断与治疗由于各种原因引起血小板减少症的重要检测项目。血小板计数是指单位体积血液中所含的血小板数目。当血小板计数低于一定数值(例如20×10 9/L)时，一般认为必须给患者进行血小板输血，否则患者将有致命的出血危险。然而，另一方面，不必要的输血会导致临床费用浪费以及由输血所导致的临床风险，例如血小板输注无效、输血后紫癜等。因此，准确计数血小板具有非常重要临床意义。
目前，血液细胞分析仪采用阻抗法或光学法对血液样本中的血小板进行计数。对于正常样本，血液细胞分析仪能够准确计数血小板，但对于异常样本(比如血小板聚集样本)，血液细胞分析仪的血小板计数结果偏差较大。当检验医生判断液细胞分析仪的血小板计数结果出现异常时，需要在显微镜下对血液样本进行复检，确认血小板计数值，依靠人的经验来判断血小板是否真的出现了异常。这不仅对检验医生提出了更高的要求，而且也容易出现人为错误，效率低下。
发明内容
本申请实施例提供一种样本分析系统、细胞图像分析仪、方法及计算机可读存储介质，其能够高效地且自动化地检测异常样本中的血小板，减少甚至无需人工介入，提高了血液检测效率和准确性。
本申请第一方面提供一种样本分析系统，包括：
血液细胞分析仪，配置用于检测血液样本中的细胞，以获得血液检测结果；
涂片制备装置，配置用于制备血液样本的涂片；
细胞图像分析仪，配置用于对涂片中的细胞进行图像拍摄和分析；
运送装置，包括第一传输轨道和第二传输轨道，第一传输轨道配置用于将血液样本从所述血液细胞分析仪运送到所述涂片制备装置，第二传输轨道配置用于将涂片从所述涂片制备装置运送到所述细胞图像分析仪；
控制装置，与所述血液细胞分析仪、所述涂片制备装置、所述细胞图像分析仪和所述运送装置通信连接，并且配置用于：
从所述血液细胞分析仪获取待测血液样本的血液检测结果，
当根据所述血液检测结果判断所述待测血液样本中存在血小板异常时，指示所述第一传输轨道将所述待测血液样本运送至所述涂片制备装置，指示所述涂片制备装置制备所述待测血液样本的待测涂片，指示所述第二传输轨道将所述待测涂片运送至所述细胞图像分析仪，以及指示所述细胞图像分析仪拍摄所述待测涂片的细胞图像并分析所述细胞图像，
其中，当所述细胞图像分析仪根据所述细胞图像判断所述待测血液样本中不存在血小板聚集时，所述细胞图像分析仪根据所述细胞图像估计所述待测血液样本的血小板计数。
本申请第二方面提供一种样本分析系统，包括：
血液细胞分析仪，配置用于检测血液样本中的细胞，以获得血液检测结果；
涂片制备装置，配置用于制备血液样本的涂片；
细胞图像分析仪，配置用于对涂片中的细胞进行图像拍摄和分析；
运送装置，包括第一运送轨道和第二运送轨道，第一运送轨道配置用于将血液样本从所述血液细胞分析仪运送到所述涂片制备装置，第二运送轨道配置用于将涂片从所述涂片制备装置运送到所述细胞图像分析仪；
控制装置，与所述血液细胞分析仪、所述涂片制备装置、所述细胞图像分析仪和所述运送装置通信连接，并且配置用于：
从所述血液细胞分析仪获取待测血液样本的血液检测结果，
当根据所述血液检测结果判断所述待测血液样本中存在血小板异常时，指示所述第一运送轨道将所述待测血液样本运送至所述涂片制备装置，指示所述涂片制备装置制备所述待测血液样本的待测涂片，指示所述第二运送轨道将所述待测涂片运送至所述细胞图像分析仪，以及指示所述细胞图像分析仪拍摄所述待测涂片的细胞图像，
其中，所述细胞图像分析仪根据所述细胞图像估计所述待测血液样本的血小板计数和/或判断所述待测血液样本中是否存在血小板聚集。
本申请第三方面提供一种用于分析涂片的细胞图像分析仪，包括：
数字成像装置，具有多个物镜和数字相机，所述数字相机用于在所述物镜下对由待测血液样本制备的涂片中的细胞进行图像拍摄；
涂片移动装置，用于调整所述数字成像装置与所述涂片的相对位置；
控制器，包括受处理器控制的存储器，所述存储器存储有可使处理器执行如下操作的指令：
控制所述涂片移动装置将所述涂片调整到预定位置，
控制所述数字相机在所述物镜下拍摄所述涂片在所述预定位置中的细胞图像，
当根据所述细胞图像判断所述待测血液样本中不存在血小板聚集时，根据所述细胞图像估计所述待测血液样本的血小板计数。
本申请第四方面提供一种自动检测血小板的方法，包括：
血液细胞分析仪获取待测血液样本的血液检测结果；
当根据所述血液检测结果判断所述待测血液样本中存在血小板异常时，涂片制备装置制备所述待测血液样本的待测涂片，以及细胞图像分析仪获取所述待测涂片的细胞图像；
当所述细胞图像分析仪根据所述细胞图像判断所述待测血液样本中不存在血小板聚集时，所述细胞图像分析仪根据所述细胞图像估计所述待测血液样本的血小板计数。
本申请第五方面提供一种自动检测血小板的方法，包括：
获取血液细胞分析仪对待测血液样本的血液检测结果；
当根据所述血液检测结果判断所述待测血液样本中存在血小板异常时，
第一运送轨道将所述待测血液样本从所述血液细胞分析仪运送至涂片制备装置，
所述涂片制备装置制备所述待测血液样本的待测涂片，
第二运送轨道将所述待测涂片从所述涂片制备装置制备运送至细胞图像分析仪，
所述细胞图像分析仪拍摄所述待测涂片的细胞图像，并根据所述细胞图像估计所述待测血液样本的血小板计数和/或根据所述细胞图像判断所述待测血液样本中是否存在血小板聚集。
本申请第六方面提供一种计算机可读存储介质，所述计算机存储介质存储有计算机程序，所述计算机程序包括程序指令，所述程序指令当被处理器执行时使所述处理器执行根据本申请第四方面或本申请第五方面所述的方法。
本申请实施例中，血液细胞分析仪获取待测血液样本的血液检测结果；在待测血液样本的血液检测结果表明待测血液样本中存在血小板异常的情况下，涂片制备装置制备所述待测血液样本的待测涂片，细胞图像分析仪获取待测涂片的细胞图像；细胞图像分析仪根 据所述细胞图像判断待测血液样本中是否存在血小板聚集和/或估计待测血液样本的血小板计数，或者细胞图像分析仪根据所述细胞图像判断待测血液样本中不存在血小板聚集时估计待测血液样本的血小板计数。也就是说，本申请实施例能够自动根据血液细胞分析仪的检测结果，判断待测血液样本是否存在血小板异常，并且在判断待测血液样本中存在血小板异常的情况下自动将待测样本运送至涂片制备装置制备待测涂片，然后自动将待测涂片运送至细胞图像分析仪进行图像拍摄和分析，以进一步通过细胞图像分析仪自动判断待测血液样本中是否存在血小板聚集并估计待测血液样本的血小板计数。由此能够高效且自动化地检测异常样本中的血小板，减少人工介入，甚至无需人工介入，极大减轻了检验医生的负担，减少人工错误。此外，相比于通过显微镜人工统计血小板数量，通过细胞图像分析仪能够准确估算待测血液样本中的血小板计数，不需检验医生长时间在显微镜下计数血小板，提高了血小板计数效率，同时减少了人工误差。
附图说明
为了更清楚地说明本申请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，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1是本申请实施例提供的一种样本分析系统的结构示意图；
图2和图3是本申请实施例提供的一种涂片制备装置的不同视角的结构立体图；
图4是本申请实施例提供的一种细胞图像分析仪的结构示意图；
图5是本申请实施例提供的另一种细胞图像分析仪的结构示意图；
图6是本申请实施例提供的一种涂片的结构示意图；
图7是本申请实施例提供的一种控制装置的结构示意图；
图8至图12是本申请不同实施例提供的一种自动检测血小板的方法的流程示意图；
图13为本申请实施例提供的一种血小板计数方法的流程示意图；
图14是本申请实施例提供的一种细胞图像的灰度直方图；
图15是本申请实施例提供的一种深度神经网络结构示意图；
图16为本申请实施例提供的一种血小板检测装置的结构示意图；
图17是本申请实施例提供的另一种血小板检测装置的结构示意图。
具体实施方式
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，所描述的实施例仅仅是本申请一部分实施例，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。
本申请的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别不同对象，而不是用于描述特定顺序。此外，术语“包括”和“具有”以及它们任何变形，意图在于覆盖不排他的包含。例如包含了一系列步骤或单元的过程、方法、系统、产品或设备没有限定于已列出的步骤或单元，而是可选地还包括没有列出的步骤或单元，或可选地还包括对于这些过程、方法、产品或设备固有的其他步骤或单元。
在本申请中提及“实施例”意味着，结合实施例描述的特定特征、结构或特性可以包含在本申请的至少一个实施例中。在说明书中的各个位置出现该短语并不一定均是指相同的实施例，也不是与其它实施例互斥的独立的或备选的实施例。本领域技术人员显式地和隐式地理解的是，本申请所描述的实施例可以与其它实施例相结合。
下面对本申请实施例进行详细介绍。
请参阅图1，图1是本申请实施例提供的一种样本分析系统的结构示意图。如图1所示，该样本分析系统100包括血液细胞分析仪110、涂片制备装置120、细胞图像分析仪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，细胞图像分析仪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和细胞图像分析仪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仪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。在一些实施例中，控制装置140通过调度控制器(未示出)间接地与第一传输轨道150和第二传输轨道160电连接。
在本申请实施例中，控制装置140配置用于：
从血液细胞分析仪110获取待测样本(例如血液样本)的样本检测结果；
当根据所述样本检测结果判断所述待测样本中存在血小板异常时，指示第一运送轨道150将所述待测样本(以装载在样本管中的方式)运送至涂片制备装置120，指示涂片制备装置120制备待测样本的待测涂片，指示第二运送轨道160将待测涂片运送至细胞图像分析仪130，以及指示细胞图像分析仪130拍摄待测涂片的细胞图像并根据所述细胞图像估计待测样本的血小板计数和/或判断待测样本中是否存在血小板聚集，或者细胞图像分析仪130根据所述细胞图像判断所述待测样本中不存在血小板聚集时再根据所述细胞图像估计待测样本的血小板计数或提示是否要根据所述细胞图像对所述待测样本的血小板计数进行估计。
本申请实施例中，样本分析系统100能够高效地且自动化地检测异常样本中的血小板，减少人工介入，甚至无需人工介入。细胞图像分析仪可以较准确估算待测血液样本中血小板计数。与人工统计的方式相比，本申请实施例不需检验人员长时间在显微镜下计数血小板，提高了血小板计数效率，同时减少了人工误差。
以血液样本为例，说明样本分析系统100的工作流程：
首先，血液细胞分析仪110对试管架10上的待测血液样本11进行检测，获取待测血液样本的血液检测结果(血液检测结果可以包括血小板检测结果、红细胞检测结果、白细胞检测结果等)。当控制装置140根据血液检测结果判断需要对试管架10上的待测血液样本11进行复检(比如，待测血液样本的血液检测结果表明检测待测血液样本中存在血小板低值异常)时，控制装置140指示第一传输轨道150将装载有需要复检的待测血液样本的试管架运送到涂片制备装置120，以便制备涂片21。涂片制备装置120将制备好的涂片21收纳在玻片篮20中，通过第二传输轨道160将收纳有涂片21的玻片篮20运送至细胞图像分析仪130，以便细胞图像分析仪130拍摄涂片的细胞图像并对拍摄的细胞图像进行分析，当分析出待测血液样本中不存在血小板聚集时估计待测血液样本的血小板计数，或者直接估计待测血液样本的血小板计数。
在本申请一实施例中，如图1所示，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首先经由第一传输轨道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，首先需要将试管架10运送至涂片制备装置120制备待测样本的涂片。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制备待测样本的涂片，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仪130，细胞图像分析仪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)，其可设置在血液分析仪110、细胞图像分析仪130或控制装置140上，或者单独设置。显示装置可以包括显示屏，比如，液晶显示屏、OLED显示屏等。所述显示装置配置用于显示待测样本中是否存在血小板聚集的分析结果以及显示待测样本的血小板计数。
在本申请一实施例中，血液细胞分析仪110用于对待测样本、例如血液样本进行血常规检测，以获得样本检测结果。血常规参数或者说血液检测结果可以包括WBC(white blood cell，白细胞)五分类结果、WBC计数和形态参数、HGB(hemoglobin，血红蛋白)检测结果、RBC(red blood cell，红细胞)以及PLT(blood platelet，血小板)计数和形态参数中的至少一种或多种组合。
血液细胞分析仪110通常包括采样装置、样本制备装置、光学检测装置、控制器(未示出)。采样装置具有采样针，用于采集血液样本并将采集的血液样本输送至样本制备装置。样本制备装置具有反应池和试剂供应部，试剂供应部贮存用于与血液样本反应的试剂并根据需要将相应的试剂供应到所述反应池。样本制备装置可包括至少一个反应池，其中至少一个反应池可配置为使得来自采样部的所述血液样本和来自试剂供应部的试剂进行反应，以制备待测试样。光学检测装置包括光源、流动室和光检测器，待测试样的粒子可在所述流动室内流动，所述光源所发射的光照射所述流动室中的粒子以产生光学信息。光检测器检测所述光学信息。控制器用于控制采样装置、样本制备装置和光学检测装置的动作并且用于获取所述光学检测装置测得的光学信息，以进一步获得血液样本的血常规检测结果。
血液细胞分析仪110还包括阻抗检测装置(未示出)。阻抗检测装置包括具有一带电极的孔的流动室。阻抗检测装置检测待测试样中的粒子通过所述孔时产生的直流阻抗，并输出反映粒子通过孔时的信息的电信号。可以理解的，血液细胞分析仪110可以通过其阻抗检测装置(即阻抗法)或光学检测装置(即光学法)检测待测血液样本中的血小板，以获得血小板阻抗法检测结果或血小板光学法检测结果。当然，血液细胞分析仪110也可以通过其阻抗检测装置和光学检测装置检测待测血液样本中的血小板，以获得血小板阻抗法检测结果和血小板光学法检测结果。例如可以当血液细胞分析仪110的阻抗检测装置测得的血小板阻抗法检测结果表明待测血液样本中存在血小板异常时，再采用血液细胞分析仪110的光学检测装置检测待测血液样本中的血小板，或者也可以同时采用血液细胞分析仪110的阻抗检测装置和光学检测装置检测待测血液样本中的血小板。
血液细胞分析仪110通过其控制器与控制装置140通信连接，从而将样本检测结果传输给控制装置140，或者也可以从控制装置140接收信息。
在本申请一实施例中，图2和图3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120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(图中未示出)以及用于对玻片进行染色的染色机构125。涂片制备装置120也包括控制 器(未示出)，配置用于控制涂片制备装置120的各个机构的工作。
涂片制备装置120通过其控制器与控制装置140通信连接，从而从控制装置140接收推片指令，或者将数据发送给控制装置140。在一些实施例中，涂片制备装置120的控制器也可以直接与血液细胞分析仪110的控制器通信连接，以便从血液细胞分析仪110获取待测样本的样本分析结果，从而确定是否需要对待测样本进行推片。
当涂片制备装置120通过其控制器从控制装置140接收到推片指令后，控制器控制取样机构121进行样本提取，例如利用取样机构121中的采样装置、例如采样针1211吸取样本，并且通过未示出的管路将取样机构121所提取的样本输送给加样机构123；控制玻片装载机构122提取空白玻片，并将空白玻片装载到工作位置，以便于进行滴血操作；控制加样机构123将样本滴落到处于工作位置的空白玻片上；控制推片机构124将样本在空白玻片上推成样本薄膜形状。在完成推片动作后，涂片制备装置120的控制器还可控制干燥机构对玻片上的样本薄膜进行干燥，稳定其形态；以及也可以控制染色机构125对玻片上的样本薄膜进行染色。
本申请实施例的涂片制备装置120可以执行涂片自动制备程序，实现自动化制备涂片，提高血涂片制备效率。
在本申请一实施例中，细胞图像分析仪130也可以称为阅片机、数字细胞图像分析系统或数字显微镜。如图4所示，细胞图像分析仪130包括成像装置131、涂片移动装置132和控制器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。
如图5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例如还可以包括目镜。
细胞图像分析仪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。
细胞图像分析仪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与第二传输轨道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仪130。
细胞图像分析仪130的控制器133用于控制成像装置131、涂片移动装置132、识别装置134和/或玻片夹取装置135等的动作并且对涂片的细胞图像进行分析。此外，细胞图像分析仪130通过其控制器与控制装置140通信连接，从而能够从控制装置140接收对待测涂片进行图像拍摄和分析的指令，或者将细胞图像分析仪130的检测数据传输给控制装置140。在其他实施例中，细胞图像分析仪130的控制器133也可以直接与涂片制备装置120和/或血液细胞分析仪110的控制器通信连接，以获取拍摄指令。
在本申请一实施例中，细胞图像分析仪130的控制器133配置用于：
控制涂片移动装置132将由待测样本制备的涂片调整到预定位置；
控制数字相机1312在物镜下拍摄所述涂片在所述预定位置中的细胞图像；
当根据所述细胞图像判断待测样本中不存在血小板聚集时，根据所述细胞图像估计待测样本的血小板计数或提示是否根据所述细胞图像对所述待测血液样本的血小板计数进行估计。
细胞图像分析仪130根据细胞图像估计血小板计数的具体方法在下面还要详细描述。
在本申请一实施例中，细胞图像分析仪130进一步配置用于当待测样本中存在血小板 异常时，拍摄由所述待测样本制备的涂片的特定区域的细胞图像，该特定区域包括待测涂片的体尾交界区域、两侧边缘区域和尾部区域中的至少一个区域。如图6所示，涂片包括标签区和血膜区。标签区上打印有样本身份信息或其他标记信息，血膜区上涂抹有待测样本。样本从血膜区的头部开始往血膜区的尾部被涂抹在血膜区上。通常在血膜的两侧边缘区域更可能发现血小板聚集的情况。
在本申请一实施例中，细胞图像分析仪130进一步配置用于当待测样本中存在血小板异常时，根据由所述待测样本制备的涂片的细胞图像判断待测样本中的血小板的形态是否异常。
在本申请一实施例中，如图7，控制装置140至少包括：处理组件141、随机存取存储器(random access memory，RAM)142、只读存储器(read-only memory，ROM)143、通信接口144、存储器146和I/O接口145，其中，处理组件141、RAM142、ROM143、通信接口144、存储器146和I/O接口145通过总线147进行通信。
处理组件可以为中央处理器(central processing unit，CPU)、图形处理器(graphics processing unit，GPU)或其它具有运算能力的芯片。
存储器146中装有操作系统和应用程序等供处理器组件141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，在样本检测过程中，如有需要本地存储的数据，均可以存储到存储器146中。
输入/输出(input/output，I/O)接口146由比如通用串行总线(universal serial bus，USB)、美国电气和电子工程师学会(institute of electrical and electronics engineers，IEEE)1394或推荐标准(recommended standard)RS-232C等串行接口、小型计算机系统接口(small computer system interface，SCSI)、电子集成驱动器(integrated drive electronics，IDE)接口或IEEE1284等并行接口以及由数字/模拟(digital/analog，D/A)转换器和模拟/数字(analog/digital，A/D)转换器等组成的模拟信号接口构成。I/O接口145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140输入数据。另外，I/O接口145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140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：分析数据、仪器运行参数等。
通信接口144是可以是目前已知的任意通信协议的接口。通信接口144通过网络与外界进行通信。控制装置140可以通过通信接口144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。
在本申请实施例中，上述血液细胞分析仪110、涂片制备装置120以及细胞图像分析仪的控制器也可以具有与控制装置140类似的结构，在此不再赘述。
在本申请实施例中，控制装置140可以独立于上述血液细胞分析仪110、涂片制备装置120以及细胞图像分析仪的控制器，也可以集成到上述血液细胞分析仪110、涂片制备装置120以及细胞图像分析仪的控制器之一中，也可以包括上述血液细胞分析仪110、涂片制备装置120以及细胞图像分析仪的控制器。
以下描述本申请实施例提供的自动检测血小板的方法。本申请实施例提供方法可应用于上述样本分析系统100，尤其是可以由控制装置140实施。
请参阅图8，图8是本申请实施例提供的一种自动检测血小板的方法的流程示意图。该方法包括如下步骤：
801，血液细胞分析仪110获取待测样本的样本检测结果；
802，当根据所述样本检测结果判断所述待测样本中存在血小板异常时，涂片制备装置120制备待测样本的待测涂片；
803，细胞图像分析仪130获取所述待测涂片的细胞图像，并根据所述细胞图像判断所 述待测样本中是否存在血小板聚集，和/或估计所述待测样本中的血小板计数。
在本申请一实施例中，控制装置140分别与血液细胞分析仪110、涂片制备装置120、细胞图像分析仪130建立通信连接。上述自动检测血小板的方法的流程步骤具体如下：血液细胞分析仪110获取待测样本、例如待测血液样本的血液检测结果后，将该血液检测结果发送给控制装置140，控制装置140根据该血液检测结果判断待测样本中存在血小板异常时，控制装置140向涂片制备装置120发送涂片制备指令以及向细胞图像分析仪130发送涂片拍摄和分析指令，以便涂片制备装置120自动制备该待测样本的待测涂片以及细胞图像分析仪130获取待测涂片的细胞图像并分析。细胞图像分析仪130然后自动根据细胞图像判断待测血液样本中是否存在血小板聚集，或者根据细胞图像估计待测血液样本的血小板计数，或者根据细胞图像判断待测血液样本中是否存在血小板聚集并且估计待测血液样本的血小板计数或提示是否要根据所述细胞图像对所述待测血液样本的血小板计数进行估计。
在本申请的其他实施例中，控制装置140集成在血液细胞分析仪、涂片制备装置和细胞图像分析仪之一中。例如在一个实施例中，控制装置140集成在血液细胞分析仪中，血液细胞分析仪分别与涂片制备装置和细胞图像分析仪建立通信连接。则上述自动检测血小板的方法的流程步骤具体如下：血液细胞分析仪110获取待测血液样本的血液检测结果后，如果根据血液检测结果判断待测血液样本中存在血小板异常，则血液细胞分析仪110分别向涂片制备装置发送涂片制备120指令以及向细胞图像分析仪130发送涂片拍摄和分析指令，以便涂片制备装置120自动制备该待测样本的待测涂片以及细胞图像分析仪130获取待测涂片的细胞图像并分析。细胞图像分析仪130然后自动根据细胞图像判断待测血液样本中是否存在血小板聚集和/或根据细胞图像估计待测血液样本中的血小板计数。
进一步地，当根据所述样本检测结果判断所述待测样本中不存在血小板异常时，则不需要对所述待测样本的进行涂片制备和涂片拍摄。此时可以结束血液分析系统对待测样本的检测，或者将待测样本运送至样本分析系统的其他分析仪进行检测分析。
在本申请一实施例中，如图9所示，图9是本申请实施例提供的一种自动检测血小板的方法的流程示意图。该方法包括如下步骤：
901，血液细胞分析仪110获取待测样本的样本检测结果；
902，当根据所述样本检测结果判断所述待测样本中存在血小板异常时，涂片制备装置120制备待测样本的待测涂片；
903，细胞图像分析仪130获取所述待测涂片的细胞图像；
904，当细胞图像分析仪130根据所述细胞图像判断所述待测样本中不存在血小板聚集时，细胞图像分析仪130根据所述细胞图像估计所述待测样本的血小板计数或提示是否要根据所述细胞图像对所述待测血液样本的血小板计数进行估计。
在本申请实施例中，当细胞图像分析仪130根据细胞图像判断待测样本中不存在血小板聚集时，细胞图像分析仪130进一步根据所述细胞图像估计待测样本中的血小板计数。细胞图像分析仪130可以自动估计待测样本中的血小板计数，也可以根据用户的人工计数值半自动地估计待测样本中的血小板计数。
在其他实施例中，细胞图像分析仪130也可以提示在待测样本中不存在血小板聚集并提示用户可选择对待测样本进行计数。进一步地，细胞图像分析仪130可以输出用户可选择进行人工计数或自动计数的提示。当用户选择自动计数时，细胞图像分析仪130自动根据细胞图像估计待测样本中的血小板计数。当用户选择人工计数时，细胞图像分析仪130接收到人工计数指令后提示用户输入人工计数值，以便细胞图像分析仪130进一步估计待测样本中的血小板计数。具体血小板计数的方式在下面还要详细说明。
进一步地，图9所示的方法还包括步骤905，当细胞图像分析仪130根据所述细胞图 像判断所述待测样本中存在血小板聚集时，输出待测样本中存在血小板聚集的提示。进一步地，在该情况下，还输出对同一受试者的新的待测样本进行血小板复检的提示，即，重新获取同一受试者的新的待测样本，并将该新的待测样本运送至血液细胞分析仪110进行复检，或者运送至涂片制备装置120制备新的待测涂片，然后再运送至细胞图像分析仪130进行图像拍摄和分析。
在本申请一实施例中，如图10所示，图10是本申请实施例提供的一种自动检测血小板的方法的流程示意图。该方法包括如下步骤：
1001，血液细胞分析仪110获取待测样本的样本检测结果；
当根据所述样本检测结果判断所述待测样本中存在血小板异常时，执行步骤1002；
1002，第一运送轨道150将所述待测样本从血液细胞分析仪110运送至涂片制备装置120，
1003，涂片制备装置120制备所述待测样本的待测涂片；
1004，第二运送轨道160将所述待测涂片从涂片制备装置120制备运送至细胞图像分析仪130，
1005，细胞图像分析仪130拍摄所述待测涂片的细胞图像，并根据所述细胞图像估计所述待测样本中的血小板计数和/或根据所述细胞图像判断所述待测样本中是否存在血小板聚集。
在本申请一实施例中，血液细胞分析仪110对待测样本的样本检测结果包括血小板检测结果和红细胞检测结果中的至少一种，其中，所述血小板检测结果包括所述待测样本经血液细胞分析仪110检测到的血小板计数或者血小板浓度、血小板直方图、血小板散点图、血小板聚集提示、血小板尺寸中的至少一种，所述红细胞检测结果包括所述待测样本经血液细胞分析仪110检测到小红细胞检测结果和红细胞碎片检测结果中的至少一种。
本申请实施例中，血小板异常包括血小板计数值偏低、血小板计数值偏高、血小板直方图/散点图异常、血小板聚集、存在一定数量巨大血小板、存在一定数量的小红细胞、存在一定数量的红细胞碎片等。小红细胞，指的是直径小于正常红细胞(7～9um)。巨大血小板指直径大于7um的血小板，大血小板为直径等于3～6um的血小板，正常血小板的直径为1～3um。因此小红细胞有可能会干扰血小板计数，导致血小板偏高，巨大血小板可能会导致计数偏低。血细胞计数仪器通常采用阻抗法计数血小板，当血液样本中具有较多的小红细胞或红细胞碎片时，由于小红细胞、红细胞碎片与血小板大小相似，因此容易误将小红细胞、红细胞碎片识别为血小板，导致血小板假性偏高，引起错误的临床诊断。而当血液中具有较多的大血小板时，由于大血小板与红细胞体积大小相似，因此容易误将大血小板识别为红细胞，导致血小板计数不准确。另外，血小板聚集也容易造成血小板假性偏低，影响临床判断。在这些情况下，通常要通过细胞图像分析仪进一步确认血液样本中是否真的存在血小板异常，尤其是确认血液样本中是否存在血小板聚集或者是否存在血小板计数值偏低的情况。
就此而言，若出现如下情形中的至少一种情形，则表明待测样本中存在血小板异常：血液细胞分析仪110检测到的血小板计数超出预设数值区间、血液分析仪110提示待测样本中存在血小板聚集、血液细胞分析仪110检测到待测样本中存在一定数量的巨大血小板、血液细胞分析仪110检测到待测样本中存在一定数量的小红细胞、血液细胞分析仪110检测到待测样本中存在一定数量的红细胞碎片。
本申请实施例中，血小板计数超出预设数值区间，指的是血小板计数不处于预设数值区间范围内。比如，预设数值区间为100×10 9～1000×10 9，如果待测血液样本中的血小板数量小于100×10 9，或者大于1000×10 9，则认为存在血小板异常。
在本申请一实施例中，血液细胞分析仪110采用阻抗法或光学法对待测样本进行检测 以得到样本检测结果。其中，阻抗法依据血小板体积与红细胞体积的差异来区分血小板。然而，当样本中存在红细胞碎片、小红细胞或大血小板时，采用阻抗法检测具有较大偏差。光学法根据血小板与红细胞在被光照射时产生的散射光强度和/或荧光强度将二者区分开来。一般认为，光学法的检测相较于阻抗法要更加准确一些，但是光学法的检验成本相较于阻抗法要更高。在一些情况下，出于成本的考量可能有些血液细胞分析仪没有配置光学法装置，无法采用光学法进行检测。本申请实施例可以在准确性优先的情况下采用光学法对待测样本进行检测，在成本优先的情况下采用阻抗法对待测样本进行检测。
在本申请一实施例中，血液细胞分析仪110采用阻抗法和光学法对待测样本进行检测以得到样本检测结果。本申请实施例中，一般而言，光学法的检测相较于阻抗法要更加准确一些，但是有些情况下(比如，血小板数量较小且呈散乱分布时)光学法的准确度可能会较低，可能会低于阻抗法。因此本申请实施例采用两种方式同时检测的方法，如果两种方式检测的结果都没有出现异常，则确定检测结果正常。如果任意一种方式检测的结果出现异常，则确定检测结果异常。本申请实施例可以提高样本检测结果的检测可靠性。
在本申请一实施例中，如图11所示，血液细胞分析仪120获取待测样本的样本检测结果的步骤包括：
1101，血液细胞分析仪110采用阻抗法检测待测样本，以获得血小板阻抗法检测结果；
1102，当所述血小板阻抗法检测结果表明所述待测样本中存在血小板异常时，血液细胞分析仪110采用光学法检测所述待测样本，以获得血小板光学法检测结果，其中，所述样本检测结果包括所述血小板阻抗法检测结果和所述血小板光学法检测结果。
本申请实施例中，先采用阻抗法进行检测。如果阻抗法的检测结果异常，则进一步采用光学法进行检测。本申请实施例在血液细胞分析仪对待测血液样本的检测过程中可以兼顾检测成本和检测准确性。
图11所示的方法的其他步骤1103和1104可参考图8所示的方法的步骤802和803，在此不再赘述。
在本申请一实施例中，所述方法还包括：细胞图像分析仪130根据细胞图像判断待测样本中的血小板的形态是否异常。本申请实施例中，血小板的形态异常可以包括：大血小板、巨大血小板。大血小板为直径等于3～6um的血小板，巨大血小板指直径大于7um的血小板。如果大血小板的比率(大血小板比率是指大血小板占总的血小板的比例)偏高，则可能是血小板形成小血小板的机制发生障碍，成熟度降低，可以见于原发性血小板增多症。如果大血小板的比率偏低，说明血小板的成熟度较高。如果存在巨大血小板，则可能是由于血小板膜缺陷导致巨大血小板综合征。
在本申请一实施例中，所述方法还包括：输出所述待测样本中是否存在血小板聚集的分析结果和/或输出所述待测样本的血小板计数。其中，血小板聚集的分析结果包括细胞图像分析仪130对所述待测样本的血小板聚集分析结果，进一步包括血液细胞分析仪110对所述待测样本的血小板聚集分析结果；血小板计数包括细胞图像分析仪130对所述待测样本的血小板计数，进一步包括血液细胞分析仪110对所述待测样本的血小板计数。
本申请实施例还提供了另一种检测血小板的方法，如图12所示，所述方法包括如下步骤：
1201，获取血液细胞分析仪对待测样本的样本检测结果；
1202，当待测样本的样本检测结果表明待测样本中存在血小板异常时，获取由待测样本制备成的待测涂片的细胞图像；
1203，当根据细胞图像判断待测样本中不存在血小板聚集时，根据细胞图像估计待测样本的血小板计数或提示是否要根据细胞图像对待测样本中的血小板计数进行估计。
在本申请一实施例中，也可以不管待测样本中是否存在血小板聚集，直接根据细胞图 像估计待测样本中的血小板计数。
以下描述本申请实施例中根据细胞图像估计待测样本中的血小板计数的方法。在本申请一实施例中，细胞图像分析仪130可以根据血小板聚集结果自动估计血小板计数，也可以在提示用户之后响应于用户指令来估计血小板计数。
在本申请一实施例中，如图13所示，细胞图像分析仪130根据细胞图像估计待测样本中的血小板计数的步骤包括：
1301，识别所述细胞图像中的血小板和参考细胞；
1302，计算所述细胞图像中的血小板数量和参考细胞数量；
1303，获取所述待测样本经血液细胞分析仪110检测到的参考细胞计数；
1304，根据所述血小板数量、所述参考细胞数量以及所述参考细胞计数，估计所述待测样本的血小板计数。
本申请一实施例中，当获取到细胞图像中的血小板数量和参考细胞数量、待测样本经血液细胞分析仪110检测到的参考细胞计数，可以得到细胞图像中血小板数量和参考细胞数量的比值，将细胞图像中血小板数量和参考细胞数量的比值与待测样本的参考细胞计数相乘，即可估计待测样本的血小板计数。也就是说，可通过如下公式估计待测样本的血小板计数：
Figure PCTCN2019123819-appb-000001
其中，N PLT为待估计的血小板计数，N RFBC为待测样本经血液细胞分析仪110检测的参考细胞计数，M PLT为细胞图像中的血小板数量，M RFBC为细胞图像中的参考细胞数量。
在本申请实施例中，当获取到的参考细胞数量不满足条件时，细胞图像分析仪130可以继续获取待测涂片的其他区域的细胞图像，以增大统计量，从而更准确地根据细胞图像来估计待测样本中的血小板计数。
在本申请一实施例中，采用图像分割方法或深度学习方法识别所述细胞图像中的血小板和参考细胞。
在本申请一实施例中，步骤1301包括：基于所述细胞图像中细胞和背景的特征差异，识别所述细胞图像中的细胞区域；基于不同细胞的特征差异，对所述细胞区域中的细胞进行分类，识别出所述细胞区域中的血小板区域和参考细胞区域；相应地，步骤1302包括：统计所述血小板区域中的血小板数量以及所述参考细胞区域中的参考细胞数量。
本申请一实施例中，细胞图像中细胞和背景的特征差异可以包括灰度差异、特定颜色空间分量的差异。比如，可以根据细胞图像的灰度直方图确定细胞图像中的细胞区域和背景区域。
例如，细胞图像分析仪可以获取细胞图像的灰度直方图，根据灰度直方图中细胞区域和背景区域的灰度差异来识别细胞图像中的细胞区域。
具体的，请参阅图14，图14是本申请实施例公开的一种细胞图像的灰度直方图。如图14所示，灰度直方图的横坐标为细胞图像的像素点的灰度值，纵坐标为该灰度值对应的像素点个数。其中，细胞区域的灰度值处于100-200之间，背景的灰度值处于200-255之间。细胞图像分析仪可以将细胞图像的像素点的灰度值处于100-200之间的区域确定为细胞区域，将细胞图像的像素点的灰度值处于200-255之间的区域确定为背景区域。
本申请一实施例中，细胞图像分析仪可基于边缘检测的图像分割方法，根据细胞与背景在颜色、亮度上存在明显的差异，即存在较明显的边缘，利用梯度可检测细胞的边缘，从而实现细胞与背景的分离。
本申请一实施例中，特定颜色空间包括红绿蓝(red green blue，RGB)颜色空间、色 调饱和度明度(hue saturation value，HSV)颜色空间、色调饱和度亮度(hue saturation intensity，HSI)颜色空间、Lab颜色空间、亮度色度(luminance chrominance，YUV)颜色空间、亮度蓝色色度红色色度(luminance chrominance blue chrominance red)YCbCr颜色空间中的一种。特定颜色空间的分量包括RGB颜色空间中任一分量或HSV颜色空间中任一分量或HSI颜色空间中任一分量或Lab颜色空间中任一分量或YUV颜色空间中任一分量或YCbCr颜色空间中任一分量。
例如，参考细胞为红细胞时，细胞图像分析仪可以根据细胞图像在HSI颜色空间的S分量的差异来识别红细胞和血小板。比如，对于8位HSI而言，血小板和有核细胞(比如白细胞)的S分量一般处于150到255之间，红细胞的S分量一般处于0-150之间，可以根据细胞图像中S分量的大小来将细胞图像中的红细胞区域与包括血小板和白细胞的第一区域区分开。细胞图像分析仪再根据第一区域区中连通区域的大小来区分血小板区域和白细胞区域。
其中，连通区域包括八连通区域或四连通区域。八连通区域指的是从区域内每一像素出发，可通过八个方向，即上、下、左、右、左上、右上、左下、右下这八个方向的移动的组合，在不越出区域的前提下，到达区域内的任意像素。四连通区域指的是从区域内每一像素出发，可通过四个方向，即上、下、左、右这四个方向的移动的组合，在不越出区域的前提下，到达区域内的任意像素。
一般而言，白细胞核的直径大于血小板的直径。细胞图像分析仪可以根据白细胞核和血小板的细胞尺寸来区分白细胞和血小板。
在本申请实施例中，细胞图像分析仪基于不同细胞的特征差异，使用支持向量机方法、人工神经网络方法或贝叶斯方法中的一种对细胞区域中的细胞进行分类，识别出细胞区域中的血小板区域和参考细胞区域。
本申请实施例中，以参考细胞为红细胞为例。细胞图像分析仪130对红细胞区域内的多连通区域进行填充后可以统计红细胞区域内的单连通区域的数量，即可得到细胞图像中的红细胞数量。细胞图像分析仪130统计血小板区域中血小板连通区域的数量，即可得到指定区域的细胞图像中的血小板数量。
在本申请实施例中，单连通区域定义如下：设D是一区域，若属于D内任一简单闭曲线的内部都属于D，则称D为单连通区域，单连通区域也可以这样描述：D内任一封闭曲线所围成的区域内只含有D中的点。更通俗地说，单连通区域是没有“洞”的区域。多连通区域定义如下：设D是一区域，若属于D内存在一条简单闭曲线，并且该简单闭曲线的内部不属于D，则称D为多连通区域。更通俗地说，多连通区域是有“洞”的区域。
可选的，若参考细胞包括红细胞，细胞图像分析仪130统计血小板区域中的血小板数量，统计红细胞区域中的红细胞数量；若参考细胞包括白细胞，细胞图像分析仪130统计血小板区域中的血小板数量，统计白细胞区域中对应的白细胞数量；若参考细胞包括红细胞与白细胞组合，细胞图像分析仪130统计血小板区域中的血小板数量，统计红细胞区域中的红细胞数量，统计白细胞区域中对应的白细胞数量。
可选的，细胞图像分析仪130统计血小板区域中的血小板数量，具体可以包括如下步骤：
统计所述血小板区域中的连通区域的数量，将所述血小板区域中的连通区域的数量作为所述血小板区域中的血小板数量。
可选的，细胞图像分析仪130统计参考细胞区域中的参考细胞数量，具体可以包括如下步骤：
若所述参考细胞包括红细胞，对所述红细胞区域中多连通区域进行空洞填充形成单连通区域，根据所述红细胞区域中的单连通区域的参数确定所述参考细胞区域中的参考细胞 数量；
若所述参考细胞包括白细胞，统计所述白细胞区域中的连通区域的数量，将所述白细胞区域中的连通区域的数量作为所述参考细胞区域中的参考细胞数量；
若所述参考细胞包括红细胞与白细胞组合，统计所述白细胞区域中的连通区域的数量，根据所述白细胞区域中的连通区域的数量确定所述参考细胞区域中的白细胞数量；对所述红细胞区域中多连通区域进行空洞填充进而形成单连通区域，根据所述红细胞区域中的单连通区域的参数确定所述参考细胞区域中的红细胞数量；将所述参考细胞区域中的白细胞数量和所述参考细胞区域中的红细胞数量之和作为所述参考细胞区域中的参考细胞数量，或将所述参考细胞区域中的白细胞数量和所述参考细胞区域中的红细胞数量分别作为所述参考细胞区域中的参考细胞数量。
可选的，所述单连通区域的参数包括所述单连通区域的数量；所述细胞图像分析仪根据所述红细胞区域中的单连通区域的参数确定所述参考细胞区域中的参考细胞数量，包括：
统计所述红细胞区域中的单连通区域的数量，将所述红细胞区域中单连通区域的数量作为所述参考细胞区域中的参考细胞数量；
所述细胞图像分析仪根据所述红细胞区域中的单连通区域的参数确定所述参考细胞区域中的红细胞数量，包括：
统计所述红细胞区域中的单连通区域的数量，将所述红细胞区域中单连通区域的数量作为所述参考细胞区域中的红细胞数量。
本申请实施例中可以应用于红细胞区域中没有其他杂质(比如，白细胞的胞浆、血小板透明区域)影响的情况，只需要统计红细胞区域的单连通区域的数量即可准确统计参考细胞区域的红细胞数量。
可选的，所述单连通区域的参数包括所述单连通区域的数量和所述单连通区域的面积；所述细胞图像分析仪根据所述红细胞区域中的单连通区域的参数确定所述参考细胞区域中的参考细胞数量，包括：
统计所述红细胞区域中的面积处于预设面积阈值区间的单连通区域的数量，将所述红细胞区域中的面积处于预设面积阈值区间的单连通区域的数量作为所述参考细胞区域中的参考细胞数量；
所述细胞图像分析仪根据所述红细胞区域中的单连通区域的参数确定所述参考细胞区域中的红细胞数量，包括：
统计所述红细胞区域中的面积处于预设面积阈值区间的单连通区域的数量，将所述红细胞区域中的面积处于预设面积阈值区间的单连通区域的数量作为所述参考细胞区域中的红细胞数量。
本申请实施例中，当红细胞区域中存在杂质影响的情况时，比如，红细胞区域中存在白细胞的胞浆时，白细胞的胞浆形成的连通域被填充后，也会形成单连通区域，如果不考虑单连通区域的面积，这些单连通区域会对红细胞的统计结果造成影响。
一般而言，白细胞的胞浆形成的单连通域的面积要大于红细胞形成的单连通域，血小板透明区域形成的单连通域的面积要小于红细胞形成的单连通域。可以设置预设面积阈值区间，使得红细胞形成的单连通域的面积落入该设置预设面积阈值区间内，使得白细胞的胞浆形成的单连通域的面积不会落入该设置预设面积阈值区间内，使得血小板透明区域形成的单连通域的面积不会落入该设置预设面积阈值区间内。
在本申请一实施例中，在参考细胞包括红细胞与白细胞组合的情况下，细胞图像分析仪统计红细胞区域中的红细胞数量，统计白细胞区域中的白细胞数量，将红细胞区域中的红细胞数量作为第一参考细胞数量，将白细胞区域中的白细胞数量作为第二参考细胞数量。
细胞图像分析仪获取待测样本中参考细胞的数量，基于细胞图像中血小板数量和第一 参考细胞数量、第二参考细胞数量、待测样本经血液细胞分析仪110获得的第一参考细胞计数、第二参考细胞计数估计待测样本的血小板计数。
在本申请一实施例中，可根据如下公式估计待测样本的血小板计数：
Figure PCTCN2019123819-appb-000002
其中，N PLT为待估计的血小板计数，N RBC为待测样本经血液细胞分析仪110检测的第一参考细胞(例如红细胞)计数，N WBC为待测样本经血液细胞分析仪110检测的第二参考细胞(例如白细胞)计数，M PLT为细胞图像中的血小板数量，M RBC为细胞图像中的参考细胞数量，M WBC为细胞图像中的参考细胞数量。其中，0<a<1，0<b<1，a+b＝1，a、b分别为加权系数。
可选的，0<a<1，0<b<1，a＞b，a+b＝1。由于血液中的红细胞数量要远多于白细胞数量，红细胞统计的误差相对较小，可以考虑将红细胞作为参考细胞时的加权系数增大，将白细胞作为参考细胞时的加权系数减小，以进一步提高血小板数量的计算精度。
在本申请一实施例中，可根据如下公式估计待测样本的血小板计数：
Figure PCTCN2019123819-appb-000003
其中，N PLT为待估计的血小板计数，N RBC为待测样本经血液细胞分析仪110检测的第一参考细胞(例如红细胞)计数，N WBC为待测样本经血液细胞分析仪110检测的第二参考细胞(例如白细胞)计数，M PLT为细胞图像中的血小板数量，M RBC为细胞图像中的参考细胞数量，M WBC为细胞图像中的参考细胞数量。
在本申请一实施例中，步骤1301包括：通过训练好的细胞类型识别模型识别所述细胞图像中的血小板和参考细胞。
本申请实施例中，细胞类型识别模型为深度神经网络模型；训练好的细胞类型识别模型是通过深度学习网络训练得到的符合要求的细胞类型识别模型，用于识别细胞图像中血小板和参考细胞，并统计细胞图像中血小板数量和参考细胞数量。
本申请实施例中血小板与红细胞个数的检测，可使用深度神经网络自动识别计数。相比于普通的人工神经网络，深度神经网络包含多个隐含层，其利用大量的样本自动学习，发现数据的分布式特征表示。采用深度神经网络的好处是不用手动提取分类特征，自动学习并挖掘数据特征，且能获得更高的识别准确率。
其中，训练好的细胞类型识别模型是通过训练数据集对细胞类型识别模型进行训练得到的。训练数据集包括用于训练的细胞图片，用于训练的细胞图片包括标注好的血小板和标注好的参考细胞。参考细胞可为红细胞、白细胞、或红细胞和白细胞。
在本申请实施例中，深度神经网络模型可使用快速区域卷积神经该网络(faster region convolutional neural networks,Faster R-CNN)网络，如图15所示。网络包含13个卷积层、4个池化层、1个感兴趣区域(region of interest，ROI)池化层、1个区域生成网络(region proposal network，RPN)、4个全连接层、1个线性回归层以及1个softmax分类层。图像输入后，利用多个卷积层和池化层自动生成特征图；然后通过RPN网络生成推荐的备选区域，也就是其检测到的细胞区域；将这些区域信息传递到ROI池化层，把各个区域降低到同样的大小；再将同样大小的区域信息传递到全连接层，最终利用softmax分类层，将对些区域进行细胞类别的判断；同时利用线性回归层，修正细胞的在区域内的位置。
也可对网络模型进行修改，如增加卷积层和池化层的数量，也就是增加网络深度。也可使用其他的区域卷积神经该网络(region convolutional neural networks，R-CNN)模型， 如R-CNN、Fast R-CNN、Mask R-CNN、也可使用只需看一眼(You only look once，YOLO)模型以及目标检测(Single Shot MultiBox Detector，SSD)模型。
深度神经网络需要大量已标记样本进行网络训练，其目的是为了优化网络中各个神经元的权值，以使网络性能达到最佳。网络的训练可使用梯度下降法，根据当前网络的预测输出与实际结果的误差，不断调整所有神经元的权值，最终使得网络的预测输出与实际结果的误差最小化。
在本申请一实施例中，细胞图像分析仪130根据细胞图像估计待测样本中的血小板计数的步骤包括：
识别所述细胞图像中的血小板并计算所述细胞图像中的血小板数量；
根据所述血小板数量与预定系数的乘积，估计所述待测样本的血小板计数。
在本申请实施例中，预定系数可以是预先存储在细胞图像分析仪130的控制器的存储介质中的恒定值。该预定系数例如可以根据经验确定。在一些实施例中，预定系数可以由用户自行定义，然后输入到细胞图像分析仪130中。
参考细胞可以是白细胞和红细胞中的至少一种，优选至少包括红细胞。
在本申请一实施例中，由用户根据细胞图像识别待测样本的血小板并计数，然后将计数值输入到细胞图像分析仪130中。也就是说，细胞图像分析仪130实施下列步骤：
接收由外部输入的通过所述细胞图像计算的血小板数量；
根据所述血小板数量与预定系数的乘积，估计所述待测样本的血小板计数。
在本申请另一实施例中，细胞图像分析仪130实施下列步骤：
接收由外部输入的通过所述细胞图像计算的血小板数量；
识别所述细胞图像中参考细胞并计算参考细胞数量；
获取所述待测血液样本经所述血液细胞分析仪检测到的参考细胞计数；
根据所述血小板数量、所述参考细胞数量以及所述参考细胞计数，估计待测样本的血小板计数。
本申请实施例还提供的一种血小板检测装置，如图16所示，该血小板检测装置1600可以包括第一检测单元1601、图像获取单元1602、第二检测单元1603和估计单元1604。第一检测单元1601用于获取血液细胞分析仪对待测样本的样本检测结果并根据样本检测结果判断所述待测样本中是否存在血小板异常。图像获取单元1602用于在第一检测单元1601判断所述待测样本中存在血小板异常时获取由所述待测样本制备成的待测涂片的细胞图像。第二检测单元1603用于根据所述细胞图像判断所述待测样本中是否存在血小板聚集。估计单元1604用于在第二检测单元1603判断所述待测样本中不存在血小板聚集时根据所述细胞图像估计所述待测样本的血小板计数或提示是否要根据所述细胞图像估计所述待测样本的血小板计数。
上述主要从方法侧执行过程的角度对本申请实施例的方案进行了介绍。可以理解的是，为了实现上述功能，其包含了执行各个功能相应的硬件结构和/或软件模块。本领域技术人员应该很容易意识到，结合本文中所提供的实施例描述的各示例的单元及算法步骤，本申请能够以硬件或硬件和计算机软件的结合形式来实现。某个功能究竟以硬件还是计算机软件驱动硬件的方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
本申请实施例可以根据上述方法示例对血小板检测装置进行功能单元的划分，例如，可以对应各个功能划分各个功能单元，也可以将两个或两个以上的功能集成在一个处理单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。需要说明的是，本申请实施例中对单元的划分是示意性的，仅仅为一种逻辑功能划分，实 际实现时可以有另外的划分方式。
本申请实施例还提供了另一种血小板检测装置，如图17所示，该血小板检测装置1700包括处理器1701、存储器1702和通信接口1703，处理器1701、存储器1702和通信接口1703可以通过通信总线1704相互连接。所述存储器1702用于存储计算机程序，所述计算机程序包括程序指令，所述处理器1701被配置用于调用所述程序指令，执行上述实施例中记载的任何一种血小板检测方法的部分或全部步骤。
本申请实施例还提供一种计算机存储介质，其中，该计算机存储介质存储用于电子数据交换的计算机程序，该计算机程序使得计算机执行上述实施例中记载的任何一种血小板检测方法的部分或全部步骤。
本申请实施例还提供一种计算机程序产品，所述计算机程序产品包括存储了计算机程序的非瞬时性计算机可读存储介质，该计算机程序使得计算机执行上述实施例中记载的任何一种血小板检测方法的部分或全部步骤。
需要说明的是，对于前述的各方法实施例，为了简单描述，故将其都表述为一系列的动作组合，但是本领域技术人员应该知悉，本申请并不受所描述的动作顺序的限制，因为依据本申请，某些步骤可以采用其他顺序或者同时进行。其次，本领域技术人员也应该知悉，说明书中所描述的实施例均属于优选实施例，所涉及的动作和模块并不一定是本申请所必须的。
在上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详述的部分，可以参见其他实施例的相关描述。
作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在申请明各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件程序模块的形式实现。
所述集成的单元如果以软件程序模块的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储器中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储器中，包括若干指令用以使得一台计算机设备(可为个人计算机、服务器或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储器包括：U盘、只读存储器(read-only memory，ROM)、随机存取存储器(random access memory，RAM)、移动硬盘、磁碟或者光盘等各种可以存储程序代码的介质。
本领域普通技术人员可以理解上述实施例的各种方法中的全部或部分步骤是可以通过程序来指令相关的硬件来完成，该程序可以存储于一计算机可读存储器中，存储器可以包括：闪存盘、只读存储器、随机存取器、磁盘或光盘等。
以上提及的特征，只要在本申请的范围内是有意义的并且不会相互矛盾，均可以任意相互组合。针对本申请的样本分析系统所说明的优点和特征以相应的方式适用于本申请的细胞图像分析仪、血小板检测方法、血小板检测装置、计算机可读存储介质以及计算机程序产品，反之亦然。
以上对本申请实施例进行了详细介绍，本文中应用了具体个例对本申请的原理及实施方式进行了阐述，以上实施例的说明只是用于帮助理解本申请的方法及其核心思想；同时，对于本领域的一般技术人员，依据本申请的思想，在具体实施方式及应用范围上均会有改变之处，综上所述，本说明书内容不应理解为对本申请的限制。

Claims (32)

  1. 一种样本分析系统，其特征在于，所述样本分析系统包括：
    血液细胞分析仪，配置用于检测血液样本中的细胞，以获得血液检测结果；
    涂片制备装置，配置用于制备血液样本的涂片；
    细胞图像分析仪，配置用于对涂片中的细胞进行图像拍摄和分析；
    运送装置，包括第一传输轨道和第二传输轨道，第一传输轨道配置用于将血液样本从所述血液细胞分析仪运送到所述涂片制备装置，第二传输轨道配置用于将涂片从所述涂片制备装置运送到所述细胞图像分析仪；
    控制装置，与所述血液细胞分析仪、所述涂片制备装置、所述细胞图像分析仪和所述运送装置通信连接，并且配置用于：
    从所述血液细胞分析仪获取待测血液样本的血液检测结果；
    当根据所述血液检测结果判断所述待测血液样本中存在血小板异常时，指示所述第一传输轨道将所述待测血液样本运送至所述涂片制备装置，指示所述涂片制备装置制备所述待测血液样本的待测涂片，指示所述第二传输轨道将所述待测涂片运送至所述细胞图像分析仪，以及指示所述细胞图像分析仪拍摄所述待测涂片的细胞图像并分析所述细胞图像；
    其中，当所述细胞图像分析仪根据所述细胞图像判断所述待测血液样本中不存在血小板聚集时，所述细胞图像分析仪根据所述细胞图像估计所述待测血液样本的血小板计数。
  2. 根据权利要求1所述的样本分析系统，其特征在于，所述细胞图像分析仪进一步配置用于：
    当所述待测血液样本中存在血小板异常时，拍摄所述待测涂片的特定区域的细胞图像，所述特定区域包括所述待测涂片的体尾交界区域、两侧边缘区域和尾部区域中的至少一个区域。
  3. 根据权利要求1或2所述的样本分析系统，其特征在于，所述细胞图像分析仪进一步配置用于在根据所述细胞图像估计所述待测血液样本中的血小板计数时执行以下步骤：
    识别所述细胞图像中的血小板和参考细胞；
    计算所述细胞图像中的血小板数量和参考细胞数量；
    获取所述待测血液样本经所述血液细胞分析仪检测到的参考细胞计数；
    根据所述血小板数量、所述参考细胞数量以及所述参考细胞计数，估计所述待测血液样本的血小板计数。
  4. 根据权利要求3所述的样本分析系统，其特征在于，所述细胞图像分析仪进一步配置用于：
    采用图像分割方法或深度学习方法识别所述细胞图像中的血小板和参考细胞，并统计所述细胞图像中的血小板数量和参考细胞数量。
  5. 根据权利要求4所述的样本分析系统，其特征在于，所述细胞图像分析仪进一步配置用于：
    基于所述细胞图像中细胞和背景的特征差异，识别所述细胞图像中的细胞区域；
    基于不同细胞的特征差异，对所述细胞区域中的细胞进行分类，识别出所述细胞区域中的血小板区域和参考细胞区域；
    统计所述血小板区域中的血小板数量以及所述参考细胞区域中的参考细胞数量。
  6. 根据权利要求4所述的样本分析系统，其特征在于，所述细胞图像分析仪进一步配置用于：
    通过训练好的细胞类型识别模型识别所述细胞图像中的血小板和参考细胞，并统计所述细胞图像中的血小板数量和参考细胞数量。
  7. 根据权利要求3至6中任一项所述的样本分析系统，其特征在于，所述参考细胞包括红细胞。
  8. 根据权利要求1或2所述的样本分析系统，其特征在于，所述细胞图像分析仪进一步配置用于在根据所述细胞图像估计所述待测血液样本中的血小板计数时执行以下步骤：
    识别所述细胞图像中的血小板并计算所述细胞图像中的血小板数量；
    根据所述血小板数量与预定系数的乘积，估计所述待测血液样本的血小板计数。
  9. 根据权利要求1或2所述的样本分析系统，其特征在于，所述细胞图像分析仪进一步配置用于在根据所述细胞图像估计所述待测血液样本中的血小板计数时执行以下步骤：
    接收由外部输入的通过所述细胞图像计算的血小板数量；根据所述血小板数量与预定系数的乘积，估计所述待测血液样本的血小板计数；或者，
    接收由外部输入的通过所述细胞图像计算的血小板数量；识别所述细胞图像中参考细胞并计算参考细胞数量；获取所述待测血液样本经所述血液细胞分析仪检测到的参考细胞计数；根据所述血小板数量、所述参考细胞数量以及所述参考细胞计数，估计所述待测血液样本的血小板计数。
  10. 根据权利要求1至9中任一项所述的样本分析系统，其特征在于，所述待测血液样本的血液检测结果包括血小板检测结果和红细胞检测结果中的至少一种；
    其中，所述待测血液样本的血小板检测结果包括所述待测血液样本经所述血液细胞分析仪检测到的血小板计数、血小板直方图、血小板散点图、血小板聚集提示、血小板尺寸中的至少一种；
    其中，所述待测血液样本的红细胞检测结果包括所述待测血液样本经所述血液细胞分析仪检测到小红细胞检测结果和红细胞碎片检测结果中的至少一种。
  11. 根据权利要求1至10中任一项所述的样本分析系统，其特征在于，所述血液细胞分析仪配置用于能采用阻抗法和/或光学法对所述待测血液样本进行检测以得到血小板检测结果和红细胞检测结果。
  12. 根据权利要求1至11任一项所述的样本分析系统，其特征在于，所述细胞图像分析仪进一步配置用于：
    当所述待测血液样本中存在血小板异常时，根据所述待测涂片的细胞图像判断所述待测血液样本中的血小板的形态是否异常。
  13. 根据权利要求1至12中任一项所述的样本分析系统，其特征在于，所述样本分析系统还包括：
    显示装置，设置用于显示所述待测血液样本中是否存在血小板聚集的分析结果以及显示所述待测血液样本的血小板计数。
  14. 一种样本分析系统，其特征在于，所述样本分析系统包括：
    血液细胞分析仪，配置用于检测血液样本中的细胞，以获得血液检测结果；
    涂片制备装置，配置用于制备血液样本的涂片；
    细胞图像分析仪，配置用于对涂片中的细胞进行图像拍摄和分析；
    运送装置，包括第一运送轨道和第二运送轨道，第一运送轨道配置用于将血液样本从所述血液细胞分析仪运送到所述涂片制备装置，第二运送轨道配置用于将涂片从所述涂片制备装置运送到所述细胞图像分析仪；
    控制装置，与所述血液细胞分析仪、所述涂片制备装置、所述细胞图像分析仪和所述运送装置通信连接，并且配置用于：
    从所述血液细胞分析仪获取待测血液样本的血液检测结果；
    当根据所述血液检测结果判断所述待测血液样本中存在血小板异常时，指示所述第一运送轨道将所述待测血液样本运送至所述涂片制备装置，指示所述涂片制备装置制备所述 待测血液样本的待测涂片，指示所述第二运送轨道将所述待测涂片运送至所述细胞图像分析仪，以及指示所述细胞图像分析仪拍摄所述待测涂片的细胞图像；
    其中，所述细胞图像分析仪根据所述细胞图像估计所述待测血液样本的血小板计数和/或判断所述待测血液样本中是否存在血小板聚集。
  15. 一种用于分析涂片的细胞图像分析仪，包括：
    数字成像装置，具有多个物镜和数字相机，所述数字相机用于在所述物镜下对由待测血液样本制备的涂片中的细胞进行图像拍摄；
    涂片移动装置，用于调整所述数字成像装置与所述涂片的相对位置；
    控制器，包括受处理器控制的存储器，所述存储器存储有可使处理器执行如下操作的指令：
    控制所述涂片移动装置将所述涂片调整到预定位置；
    控制所述数字相机在所述物镜下拍摄所述涂片在所述预定位置中的细胞图像；
    当根据所述细胞图像判断所述待测血液样本中不存在血小板聚集时，根据所述细胞图像估计所述待测血液样本的血小板计数。
  16. 一种自动检测血小板的方法，其特征在于，所述方法包括：
    血液细胞分析仪获取待测血液样本的血液检测结果；
    当根据所述血液检测结果判断所述待测血液样本中存在血小板异常时，涂片制备装置制备所述待测血液样本的待测涂片，以及细胞图像分析仪获取所述待测涂片的细胞图像；
    当所述细胞图像分析仪根据所述细胞图像判断所述待测血液样本中不存在血小板聚集时，所述细胞图像分析仪根据所述细胞图像估计所述待测血液样本的血小板计数。
  17. 根据权利要求16所述的方法，其特征在于，所述细胞图像分析仪获取所述待测涂片的细胞图像，包括：
    获取所述待测涂片的特定区域的细胞图像，所述特定区域包括所述待测涂片的体尾交界区域、两侧边缘区域和尾部区域中的至少一个区域。
  18. 根据权利要求16或17所述的方法，其特征在于，所述细胞图像分析仪根据所述细胞图像估计所述待测血液样本的血小板计数，包括：
    识别所述细胞图像中的血小板和参考细胞；
    计算所述细胞图像中的血小板数量和参考细胞数量；
    获取所述待测血液样本经所述血液细胞分析仪检测到的参考细胞计数；
    根据所述血小板数量、所述参考细胞数量以及所述参考细胞计数，估计所述待测血液样本的血小板计数。
  19. 根据权利要求18所述的方法，其特征在于，所述识别所述细胞图像中的血小板和参考细胞，包括：
    采用图像分割方法或深度学习方法识别所述细胞图像中的血小板和参考细胞。
  20. 根据权利要求18或19所述的方法，其特征在于，所述识别所述细胞图像中的血小板和参考细胞，包括：基于所述细胞图像中细胞和背景的特征差异，识别所述细胞图像中的细胞区域；基于不同细胞的特征差异，对所述细胞区域中的细胞进行分类，识别出所述细胞区域中的血小板区域和参考细胞区域；
    所述计算所述细胞图像中的血小板数量和参考细胞数量，包括：
    统计所述血小板区域中的血小板数量以及所述参考细胞区域中的参考细胞数量。
  21. 根据权利要求18或19所述的方法，其特征在于，所述识别所述细胞图像中的血小板和参考细胞，包括：
    通过训练好的细胞类型识别模型识别所述细胞图像中的血小板和参考细胞。
  22. 根据权利要求16或17所述的方法，其特征在于，所述细胞图像分析仪根据所述 细胞图像估计所述待测血液样本的血小板计数，包括：
    识别所述细胞图像中的血小板并计算所述细胞图像中的血小板数量；
    根据所述血小板数量与预定系数的乘积，估计所述待测血液样本的血小板计数。
  23. 根据权利要求16或17所述的方法，其特征在于，所述细胞图像分析仪根据所述细胞图像估计所述待测血液样本的血小板计数，包括：
    所述细胞图像分析仪接收由外部输入的通过所述细胞图像计算的血小板数量；根据所述血小板数量与预定系数的乘积，估计所述待测血液样本的血小板计数；或者，
    所述细胞图像分析仪接收由外部输入的通过所述细胞图像计算的血小板数量；识别所述细胞图像中参考细胞并计算参考细胞数量；获取所述待测血液样本经所述血液细胞分析仪检测到的参考细胞计数；根据所述血小板数量、所述参考细胞数量以及所述参考细胞计数，估计所述待测血液样本的血小板计数。
  24. 根据权利要求16至23中任一项所述的方法，其特征在于，所述待测血液样本的血液检测结果包括血小板检测结果和红细胞检测结果中的至少一种；
    其中，所述待测血液样本的血小板检测结果包括所述待测血液样本经所述血液细胞分析仪检测到的血小板计数、血小板直方图、血小板散点图、血小板聚集提示、血小板尺寸中的至少一种；
    其中，所述待测血液样本的红细胞检测结果包括所述待测血液样本经所述血液细胞分析仪检测到小红细胞检测结果和红细胞碎片检测结果中的至少一种。
  25. 根据权利要求24所述的方法，其特征在于，若所述血液细胞分析仪检测到的血小板计数超出预设数值区间，和/或所述血液分析仪提示所述待测血液样本中存在血小板聚集，和/或所述血液细胞分析仪检测到所述待测血液样本中存在一定数量的巨大血小板，和/或所述血液细胞分析仪检测到所述待测血液样本中存在一定数量的小红细胞，和/或所述血液细胞分析仪检测到所述待测血液样本中存在一定数量的红细胞碎片，则判断所述待测血液样本中存在血小板异常。
  26. 根据权利要求16至25中任一项所述的方法，其特征在于，所述血液细胞分析仪获取所述待测血液样本的血液检测结果，包括：
    所述血液细胞分析仪采用阻抗法和/或光学法对所述待测血液样本进行检测以得到血小板检测结果和红细胞检测结果。
  27. 根据权利要求26所述的方法，其特征在于，所述血液细胞分析仪采用阻抗法和/或光学法对所述待测血液样本进行检测以得到血小板检测结果，包括：
    所述血液细胞分析仪采用阻抗法检测所述待测血液样本，以获得血小板阻抗法检测结果；
    当所述血小板阻抗法检测结果表明所述待测血液样本的血小板存在异常时，所述血液细胞分析仪采用光学法检测所述待测血液样本，以获得血小板光学法检测结果，其中，所述血液检测结果包括所述血小板阻抗法检测结果和所述血小板光学法检测结果。
  28. 根据权利要求16至27中任一项所述的方法，其特征在于，所述方法还包括：
    当所述细胞图像分析仪根据所述细胞图像判断所述待测血液样本中存在血小板聚集时，输出所述待测血液样本中存在血小板聚集的提示，和/或输出对同一受试者的新的待测血液样本进行血小板复检的提示。
  29. 根据权利要求16至28中任一项所述的方法，其特征在于，所述方法还包括：
    所述细胞图像分析仪根据所述待测涂片的细胞图像判断所述待测血液样本中的血小板的形态是否异常。
  30. 根据权利要求16至29中任一项所述的方法，其特征在于，所述方法还包括：
    输出所述待测血液样本中是否存在血小板聚集的分析结果以及输出所述待测血液样本 的血小板计数。
  31. 一种自动检测血小板的方法，其特征在于，所述方法包括：
    获取血液细胞分析仪对待测血液样本的血液检测结果；
    当根据所述血液检测结果判断所述待测血液样本中存在血小板异常时，第一运送轨道将所述待测血液样本从所述血液细胞分析仪运送至涂片制备装置，所述涂片制备装置制备所述待测血液样本的待测涂片，第二运送轨道将所述待测涂片从所述涂片制备装置制备运送至细胞图像分析仪，所述细胞图像分析仪拍摄所述待测涂片的细胞图像，并根据所述细胞图像估计所述待测血液样本的血小板计数和/或根据所述细胞图像判断所述待测血液样本中是否存在血小板聚集。
  32. 一种计算机可读存储介质，其特征在于，所述计算机存储介质存储有计算机程序，所述计算机程序包括程序指令，所述程序指令当被处理器执行时使所述处理器执行如权利要求16至31中任一项所述的方法。
PCT/CN2019/123819 2019-12-06 2019-12-06 样本分析系统及方法、细胞图像分析仪及存储介质 WO2021109152A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
PCT/CN2019/123819 WO2021109152A1 (zh) 2019-12-06 2019-12-06 样本分析系统及方法、细胞图像分析仪及存储介质
EP19955311.6A EP4071485A4 (en) 2019-12-06 2019-12-06 SAMPLE ANALYSIS SYSTEM AND METHOD, CELL IMAGE ANALYZER AND STORAGE MEDIA
CN201980102379.8A CN114729953A (zh) 2019-12-06 2019-12-06 样本分析系统及方法、细胞图像分析仪及存储介质

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2019/123819 WO2021109152A1 (zh) 2019-12-06 2019-12-06 样本分析系统及方法、细胞图像分析仪及存储介质

Publications (1)

Publication Number Publication Date
WO2021109152A1 true WO2021109152A1 (zh) 2021-06-10

Family

ID=76222175

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/123819 WO2021109152A1 (zh) 2019-12-06 2019-12-06 样本分析系统及方法、细胞图像分析仪及存储介质

Country Status (3)

Country Link
EP (1) EP4071485A4 (zh)
CN (1) CN114729953A (zh)
WO (1) WO2021109152A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114067315A (zh) * 2021-10-23 2022-02-18 广州市艾贝泰生物科技有限公司 细胞计数方法、装置、计算机设备和存储介质
CN114152557A (zh) * 2021-11-16 2022-03-08 深圳元视医学科技有限公司 基于图像分析的血细胞计数方法和系统
CN114252385A (zh) * 2021-12-16 2022-03-29 江苏康尚生物医疗科技有限公司 一种便携式白细胞亚类检测装置及方法
CN114755434A (zh) * 2022-06-13 2022-07-15 深圳市帝迈生物技术有限公司 样本分析系统及样本检测控制方法、装置、控制器和介质

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024050856A1 (zh) * 2022-09-06 2024-03-14 南京市第一医院 一种辅助血细胞分析仪判定异常血小板聚集的方法和系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1460428A1 (en) * 2003-03-21 2004-09-22 Delta Biologicals S.r.l. Modular medical analyzer
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
CN101086496A (zh) * 2007-07-16 2007-12-12 山东优生医疗科技有限公司 全自动血液常规智能分析仪及其分析方法
CN105136795A (zh) * 2015-07-20 2015-12-09 爱威科技股份有限公司 血液样本检测装置、方法和系统
CN109313209A (zh) * 2015-12-18 2019-02-05 雅培实验室 用于自动分析的系统和方法

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5301232B2 (ja) * 2008-09-30 2013-09-25 シスメックス株式会社 血球画像表示装置、検体分析システム、血球画像表示方法、及びコンピュータプログラム

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1460428A1 (en) * 2003-03-21 2004-09-22 Delta Biologicals S.r.l. Modular medical analyzer
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
CN101086496A (zh) * 2007-07-16 2007-12-12 山东优生医疗科技有限公司 全自动血液常规智能分析仪及其分析方法
CN105136795A (zh) * 2015-07-20 2015-12-09 爱威科技股份有限公司 血液样本检测装置、方法和系统
CN109313209A (zh) * 2015-12-18 2019-02-05 雅培实验室 用于自动分析的系统和方法

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4071485A4 *

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114067315A (zh) * 2021-10-23 2022-02-18 广州市艾贝泰生物科技有限公司 细胞计数方法、装置、计算机设备和存储介质
CN114152557A (zh) * 2021-11-16 2022-03-08 深圳元视医学科技有限公司 基于图像分析的血细胞计数方法和系统
CN114152557B (zh) * 2021-11-16 2024-04-30 深圳元视医学科技有限公司 基于图像分析的血细胞计数方法和系统
CN114252385A (zh) * 2021-12-16 2022-03-29 江苏康尚生物医疗科技有限公司 一种便携式白细胞亚类检测装置及方法
CN114755434A (zh) * 2022-06-13 2022-07-15 深圳市帝迈生物技术有限公司 样本分析系统及样本检测控制方法、装置、控制器和介质
CN114755434B (zh) * 2022-06-13 2022-10-21 深圳市帝迈生物技术有限公司 样本分析系统及样本检测控制方法、装置、控制器和介质

Also Published As

Publication number Publication date
CN114729953A (zh) 2022-07-08
EP4071485A1 (en) 2022-10-12
EP4071485A4 (en) 2023-04-12

Similar Documents

Publication Publication Date Title
WO2021109152A1 (zh) 样本分析系统及方法、细胞图像分析仪及存储介质
CN109564209B (zh) 对样品实施的光学测量
JP6870826B2 (ja) 側方多視点から試料を定量化するように構成された方法及び装置
US20230055601A1 (en) Urine analysis system, image capturing apparatus, urine analysis method
CN108738336B (zh) 用于多视图表征的方法和装置
CN105136795B (zh) 血液样本检测装置、方法和系统
US7936912B2 (en) Sample imaging apparatus, sample analyzing apparatus, and sample imaging method
JPS60162955A (ja) 血球自動分析装置
CN108845153B (zh) 一种白细胞粒子分析系统及方法
WO2021134664A1 (zh) 一种样本分析系统及其自动精度管理方法
WO2017145172A1 (en) System and method for extraction and analysis of samples under a microscope
JP6422824B2 (ja) 検体前処理方法及び検体前処理装置
CN114152557B (zh) 基于图像分析的血细胞计数方法和系统
US20220291196A1 (en) Target cell statistical method, apparatus, and system
WO2021134474A1 (zh) 样本分析系统及方法
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
CN109919054B (zh) 一种基于机器视觉的试剂卡自动分类的检测方法
JP7407282B2 (ja) 管アセンブリタイプを識別する装置および方法
JPH10104229A (ja) 有形成分分析装置
US11796787B2 (en) Sample image capturing system and method, and computer-readable storage medium
WO2022059467A1 (ja) 細胞分析方法及び細胞分析装置
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
EP4067881A1 (en) Smear preparation device, and sample analysis system and method
KR20230167569A (ko) 혈액 샘플의 이미지 분석 정보 제공 방법
WO2021134509A1 (zh) 样本分析系统、方法及细胞图像分析装置

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: 19955311

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2019955311

Country of ref document: EP

Effective date: 20220706