CROSS-REFERENCE TO RELATED APPLICATIONS

The present application is a continuation of U.S. application Ser. No. 17/830,729, filed on Jun. 2, 2022, which is a U.S. continuation application of International Application No. PCT/CN2019/123029, filed on Dec. 4, 2019. The disclosures of the above-referenced applications are hereby incorporated by reference in their entirety.

BACKGROUND

Blood platelet (PLT) is the smallest one of blood cells, with an average diameter of only 2 to 4 microns. Blood platelet counting refers to the number of blood platelets contained in a unit volume of blood. The number of blood platelets in a normal person's blood is maintained at a certain level. The number of blood platelets may be decreased or increased due to certain diseases. Blood platelet counting is helpful in the clinical diagnosis and differential diagnosis of hemostasis and thrombotic diseases.

Currently, blood analyzers can count blood platelets based on their small size. For normal samples, the blood analyzer can accurately count blood platelets. However, for abnormal samples (for example, increased cell debris, blood platelet aggregation, etc.), the blood platelet counting results of the blood analyzer have a large deviation. In this case, the inspector needs to re-examine under the microscope to confirm the blood platelet counting value.

The blood platelet counting method of manual re-examination under the microscope generally adopts the filling cell counting method. In the filling cell counting method, the pretreated blood is injected into the counting cell to be counted, and the number of blood platelets in the counting cell is counted with a high-power microscope. Since the volume of the counting cell is determined, the number of blood platelets per liter of blood can be calculated. However, the filling cell counting method requires the counting personnel to observe and count under the microscope for a long time, which is prone to visual fatigue and low counting efficiency.

SUMMARY

The present disclosure relates to the field of medical instruments, and in particular, to a target cell statistical method, apparatus, system and storage medium.

The embodiments of the present disclosure provide a target cell statistical method, apparatus, system and storage medium, which can improve blood platelet counting efficiency.

In a first aspect of the embodiments of the present disclosure, a target cell statistical method is provided. The method includes the following operations.

A cell image of a blood specimen is acquired by a cell image analysis apparatus. The blood specimen is derived from the blood sample to be tested.

The number of target cells and the number of reference cells in the cell image are automatically identified by the cell image analysis apparatus.

The number of reference cells in the blood sample to be tested is acquired, and the number of target cells in the blood sample to be tested is calculated based on the number of target cells and the number of reference cells in the cell image and the number of reference cells in the blood sample to be tested, by the cell image analysis apparatus.

In a second aspect of the embodiments of the present disclosure, a cell image analysis apparatus is provided. The cell image analysis apparatus includes an imaging apparatus, a specimen moving apparatus and a processor.

The imaging apparatus includes a camera and a lens group, and is configured to photograph a cell image of a blood specimen derived from a blood sample to be tested.

The specimen moving apparatus is configured to move the blood specimen relative to the imaging apparatus so that the imaging apparatus photographs a cell image of a specific region of the blood specimen.

The processor is configured to acquire a cell image of the blood specimen derived from the blood sample to be tested, and is further configured to automatically identify the number of target cells and the number of reference cells in the cell image; and is further configured to acquire the number of reference cells in the blood sample to be tested.

The processor is further configured to calculate the number of target cells in the blood sample to be tested based on the number of target cells and the number of reference cells in the cell image, and the number of reference cells in the blood sample to be tested.

In a third aspect of the embodiments of the present disclosure, a specimen analysis system is provided. The specimen analysis system includes a cell image analysis apparatus and a blood analyzer. The cell image analysis apparatus includes an imaging apparatus, a specimen moving apparatus and a processor.

The imaging apparatus includes a camera and a lens group, and is configured to photograph a cell image of a blood specimen derived from the blood sample to be tested.

The specimen moving apparatus is configured to move the blood specimen relative to the imaging apparatus so that the imaging apparatus photographs a cell image of a specific region of the blood specimen.

The blood analyzer is configured to detect the number of reference cells in the blood sample to be tested.

The processor is configured to acquire a cell image of the blood specimen, and automatically identify the number of target cells and the number of reference cells in the cell image; and is further configured to acquire the number of reference cells in the blood sample to be tested from the blood analyzer; is further configured to calculate the number of target cells in the blood sample to be tested based on the number of target cells and the number of reference cells in the cell image, and the number of reference cells in the blood sample to be tested.

In a fourth aspect of the embodiments of the present disclosure, a cell image analysis apparatus is provided. The cell image analysis apparatus includes a processor and a memory. The memory is configured to store a computer program that includes program instructions. The processor is configured to invoke the program instructions to execute the step instructions in the first aspect of the embodiments of the present disclosure.

In a fifth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program for electronic data exchange. The computer program causes the computer to execute some or all of the steps described in the first aspect of the embodiments of the present application.

In a sixth aspect of the embodiments of the present disclosure, a computer program product is provided. The computer program product includes a non-transitory computer-readable storage medium storing a computer program. The computer program is operable to cause the computer to perform some or all of the steps as described in the first aspect of the embodiments of the present disclosure. The computer program product may be a software installation package.

In the embodiments of the present disclosure, by the cell image analysis apparatus, the number of target cells and the number of reference cells in the cell image of the blood specimen may be automatically identified, and the number of target cells in the blood sample to be tested is calculated based on the number of target cells and the number of reference cells in the cell image, and the number of reference cells in the blood sample to be tested. The number of target cells in the blood sample to be tested can be accurately calculated. Compared with the manual counting method, the inspector does not need to count the target cells under the microscope for a long time, the counting efficiency of the target cells is improved, while manual errors are avoided.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the accompanying drawings required for the description of the embodiments or the prior art will be briefly introduced below. It is apparent that the drawings in the following description are only some embodiments of the present disclosure. For those of ordinary skill in the art, other accompanying drawings can also be obtained based on these accompanying drawings without any creative effort.

FIG. 1A illustrates a schematic structure diagram of a specimen analysis system disclosed in an embodiment of the present disclosure.

FIG. 1B illustrates a schematic structure diagram of another specimen analysis system disclosed in an embodiment of the present disclosure.

FIG. 2 illustrates a schematic structure diagram of a blood smear preparation apparatus disclosed in an embodiment of the present disclosure.

FIG. 3 illustrates a schematic structure diagram of a cell image analysis apparatus disclosed in an embodiment of the present disclosure.

FIG. 4 illustrates a schematic structure diagram of the operation of a cell image analysis apparatus disclosed in an embodiment of the present disclosure.

FIG. 5 illustrates a schematic flowchart of a target cell statistical method disclosed in an embodiment of the present disclosure.

FIG. 6 illustrates a schematic flowchart of another target cell statistical method disclosed in an embodiment of the present disclosure.

FIG. 7A illustrates a grayscale histogram of a cell image disclosed in an embodiment of the present disclosure.

FIG. 7B illustrates an S-component histogram of a cell image disclosed in an embodiment of the present disclosure.

FIG. 8A illustrates a schematic diagram of a cell image disclosed in the embodiment of the present disclosure.

FIG. 8B illustrates a cell image processed by grayscale threshold segmentation disclosed in an embodiment of the present disclosure.

FIG. 8C illustrates an image of a red blood cell region including red blood cells and cytoplasm disclosed in an embodiment of the present disclosure.

FIG. 8D illustrates an image of a first region including blood platelets and white blood cell nuclei disclosed in an embodiment of the present disclosure.

FIG. 8E illustrates an image of a filled red blood cell region including red blood cells and cytoplasm disclosed in an embodiment of the present disclosure.

FIG. 8F illustrates an image of a blood platelet region including blood platelets disclosed in an embodiment of the present disclosure.

FIG. 9 illustrates a schematic flowchart of another target cell statistical method disclosed in an embodiment of the present disclosure.

FIG. 10 illustrates a schematic structure diagram of a deep neural network disclosed in an embodiment of the present disclosure.

FIG. 11 illustrates an original image of a training specimen disclosed in an embodiment of the present disclosure.

FIG. 12 illustrates a red blood cell labeled image of a training specimen disclosed in an embodiment of the present disclosure.

FIG. 13 illustrates a blood platelet labeled image of a training specimen disclosed in an embodiment of the present disclosure.

FIG. 14 illustrates a red blood cell labeled image identified by a deep neural network disclosed in an embodiment of the present disclosure.

FIG. 15 illustrates a blood platelet labeled image identified by a deep neural network disclosed in an embodiment of the present disclosure.

FIG. 16A illustrates a schematic diagram of another cell image disclosed in an embodiment of the present disclosure.

FIG. 16B illustrates another cell image processed by grayscale threshold segmentation disclosed in an embodiment of the present disclosure.

FIG. 16C illustrates an image including white blood cell nuclei and blood platelets disclosed in an embodiment of the present disclosure.

FIG. 16D illustrates an image including blood platelets disclosed in an embodiment of the present disclosure.

FIG. 17 illustrates a schematic structure diagram of another cell image analysis apparatus disclosed in an embodiment of the present disclosure.

FIG. 18 illustrates a schematic structure diagram of another cell image analysis apparatus disclosed in an embodiment of the present disclosure.

DETAILED DESCRIPTION

The technical solutions in the embodiments of the present disclosure will be clearly and fully described below with reference to the drawings in the embodiments of the present disclosure. It is apparent that the described embodiments are only some embodiments of the present disclosure, but not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present disclosure.

The terms “first”, “second” and the like in the specification, the claims and the above drawings of the present disclosure are used to distinguish different objects, rather than to describe a specific order. Furthermore, the terms “including”, “having” and any variations thereof refer to non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units is not limited to the listed steps or units, but optionally may include unlisted steps or units, or optionally may further include other steps or units inherent to the process, method, product or device.

Reference to an “embodiment” in the present disclosure means that a particular feature, structure, or characteristic described with reference to the embodiment can be included in at least one embodiment of the present disclosure. The appearances of the term in various places in the specification are not necessarily all referring to the same embodiment, nor a separate or alternative embodiment that is mutually exclusive of other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described in the present disclosure may be combined with other embodiments.

The embodiments of the present disclosure will be described in detail below.

With reference to FIG. 1A, FIG. 1A illustrates a schematic structure diagram of a specimen analysis system disclosed in an embodiment of the present disclosure. As illustrated in FIG. 1A, the specimen analysis system 100 may include a cell image analysis apparatus 10 and a blood analyzer 30. The cell image analysis apparatus 10 includes an imaging apparatus 13, a specimen moving apparatus 14 and a processor 15.

The imaging apparatus 13 includes a camera 12 and a lens group 11. The imaging apparatus 13 is configured to photograph a cell image of a blood specimen derived from the blood sample to be tested.

The specimen moving apparatus 14 is configured to move the blood specimen relative to the imaging apparatus 13, so that the imaging apparatus 13 photographs a cell image of a specific region of the blood specimen.

The blood analyzer 30 is configured to detect the number of reference cells in the blood sample to be tested.

The processor 15 is configured to acquire a cell image of the blood specimen. The processor is further configured to automatically identify the number of target cells and the number of reference cells in the cell image. The processor is further configured to acquire the number of reference cells in the blood sample to be tested from the blood analyzer 30. The processor is further configured to calculate the number of target cells in the blood sample to be tested based on the number of target cells and the number of reference cells in the cell image, and the number of reference cells in the blood sample to be tested.

Optionally, the number of reference cells in the blood sample to be tested acquired by the processor may be the concentration of reference cells in the blood sample to be tested.

Optionally, as illustrated in FIG. 1A, the cell image analysis apparatus 10 may further include a display apparatus 16. The display apparatus 16 is configured to at least display the number of target cells in the blood sample to be tested. For the specific structure of the cell image analysis apparatus 10, reference may also be made to FIG. 3.

The display apparatus 16 may include a liquid crystal display, a light emitting diode (LED) display, an organic light emitting diode (OLED) display, and the like.

Optionally, that the processor 15 acquires a cell image of the blood specimen, is specifically as follows. The processor 15 acquires an input cell image of the blood specimen.

In the embodiments of the present disclosure, the processor 15 may receive cell images of blood specimens sent by other devices. The other devices may store cell images of blood specimens beforehand. The other devices may also be devices with a photographing function. For example, the processor 15 may establish a communication connection with the other device with the photographing function. After the cell images of blood specimens are photographed by other devices with the photographing function, the processor 15 acquires cell images of blood specimens input by the other devices with the photographing function.

Optionally, as illustrated in FIG. 1A, the cell analysis apparatus 10 further includes a communication apparatus 17. The communication apparatus 17 may include at least one of a communication interface, or an input/output (I/O) interface. For the specific structure of the cell image analysis apparatus 10, reference can also be made to FIG. 3.

That the processor 15 is configured to acquire the number of reference cells in the blood sample to be tested from the blood analyzer 30, includes: the processor 15 controls the communication apparatus 17 to automatically acquire the number of reference cells in the blood sample to be tested from the blood analyzer 30.

The processor 15 may also receive cell images of the blood specimens input by other devices or users through an I/O interface (for example, a USB interface). The processor 15 may also receive the cell image of the blood specimen sent by a server through the communication interface.

In the case where the cell image analysis apparatus 10 does not have a photographing function, or the photographing apparatus of the cell image analysis apparatus 10 is damaged and cannot work, an input cell image of the blood specimen can be acquired.

The imaging device 13 is configured to capture a cell image of the blood specimen through the camera 12 and the lens group 11. The blood specimen is derived from the blood sample to be tested.

That the processor 15 acquires the cell image of the blood specimen, is specifically as follows. The processor 15 acquires the cell image of the blood specimen from imaging apparatus 13.

In some embodiments, the cell image analysis apparatus may store cell images, and the user may select a cell image from the stored cell images. The processor receives the user's selection instruction, and then acquires the cell image of the blood specimen.

In the embodiments of the present disclosure, the cell image analysis apparatus, which may also be referred to as a slide reader, a cell image analysis system, or a cell image digital analysis system, can automatically photograph and analyze the blood specimen. It can also estimate the number of blood cells in the blood specimen. The cell image analysis apparatus may estimate the number of blood cells in the cell image of the blood specimen by an image processing algorithm. Blood cells can include red blood cells, white blood cells, and blood platelets.

In the embodiments of the present disclosure, the target cells and reference cells are different blood cells. For example, when the target cells are blood platelets, the reference cells may include one of red blood cells, white blood cells, or a combination of red blood cells and white blood cells. When the target cells are red blood cells, the reference cells may include one of white blood cells, blood platelets, or a combination of white blood cells and blood platelets. When the target cells are white blood cells, the reference cells may include one of red blood cells, blood platelets, or a combination of red blood cells and blood platelets.

In the embodiments of the present disclosure, the blood sample to be tested is a blood sample that needs to count target cells. The blood specimen is derived from the blood sample to be tested. Specifically, the blood specimen can be extracted from the blood sample to be tested. For example, a blood specimen may be loaded in a blood smear.

The blood smear may be prepared automatically by the blood smear preparation apparatus, or may be prepared manually, which is not limited in the embodiments of the present disclosure.

When a blood smear is manually prepared, the materials required for the preparation of blood smear include pipettes, glass slides, push slides (for example, double concave slides), etc. The preparation process of the blood smear can specifically include the following steps.

(1) A certain volume of blood sample is taken from the blood sample to be tested by using a pipette, and part of the blood sample (for example, a drop of blood sample) in the pipette is placed on one end of a glass slide.

(2) The glass slide is fixed with one hand, and the push slide is placed on one end of the glass slide obliquely with the other hand to contact the blood drop on the glass slide. The push slide is moved back from the front of the blood drop, keeping in contact with the blood drop, so that the blood drop spreads out into a line along the end of the glass slide.

(3) The push slide is moved forward by maintaining a certain angle (such as 30-45 degrees) with the glass slide, and then a thin layer of blood film can be formed on the glass slide, that is, a blood film is coated.

(4) When the blood film is completely dried in the air, a few drops of staining solution are dropped on the blood film. After fixing for a period of time (for example, 0.5-1.0 minute), the same amount or slightly more buffer solution is added dropwise, and the buffer solution is mixed with the staining solution to stain the blood film for a period of time (for example, 5-10 minutes).

(5) The staining solution is rinsed with distilled water, and after drying naturally, the prepared blood smear will be obtained.

After the prepared blood smear is obtained, the prepared blood smear can be placed under the lens group 11 for microscopic examination. The photographing apparatus (for example, a camera) 12 in the cell image analysis apparatus 10 can photograph the prepared blood smear, to obtain a cell image of the blood specimen in the blood smear.

Optionally, as illustrated in FIG. 1A, the specimen analysis system 100 further includes a blood smear preparation apparatus 20. The blood smear preparation apparatus 20 is configured to prepare the smear of the blood sample to be tested as the blood specimen to be photographed.

When the blood smear preparation apparatus 20 automatically prepares the blood smear, the blood smear preparation apparatus needs to be used. The structure of the blood smear preparation apparatus is shown in FIG. 2. The blood smear preparation apparatus 20 may include a sampling mechanism 21, a glass slide loading mechanism 22, a sample loading mechanism 23 and a push slide mechanism 24.

The sampling mechanism 21 is configured to suck a blood specimen from the blood sample to be tested.

The glass slide loading mechanism 22 is configured to move a blank glass slide to the operation position.

The sample loading mechanism 23 is configured to load the blood specimen onto the blank glass slide.

The push slide mechanism 24 is configured to smoothly spread the blood specimen on the blank glass slide to prepare a blood smear.

The sampling mechanism 21 can suck a blood specimen from a blood sample to be tested in a vessel (for example, a test tube, a cup, etc. containing blood). The sampling mechanism 21 may include a pipette for sucking liquid, a pipette control apparatus (for example, an automatic control apparatus for squeezing the pipette) for controlling the pipette to suck the liquid, a movable robotic arm. The pipette controlling apparatus is fixedly arranged on the robotic arm, and the pipette may be fixedly arranged on the robotic arm at a position where the pipette control apparatus can squeeze the pipette. The glass slide loading mechanism 22 may include a gripping apparatus (for example, a robotic arm) for gripping the blank glass slide. The sample loading mechanism 23 may include the pipette, the pipette control apparatus, and the movable robotic arm in the sampling mechanism 21. The push slide mechanism 24 may include a push slide control mechanism, a glass slide fixing mechanism, and the gripping apparatus in the glass slide loading mechanism 22.

The blood smear preparation apparatus 20 can perform an automatic blood smear preparation procedure. It controls the gripping apparatus of the glass slide loading mechanism 22 to grip the blank glass slide from the position where the blank glass slide is placed, and moves the gripped blank glass slide to the operation position. The blood smear preparation apparatus 20 controls the robotic arm of the sampling mechanism 21 to move to the position where the vessel containing the blood sample to be tested is placed, and controls the robotic arm to insert the pipette tip into the blood sample to be tested in the vessel. The blood smear preparation apparatus 20 controls the pipette control apparatus of the sampling mechanism 21 to squeeze the gas in the pipette, thereby controlling the pipette to draw a certain amount of blood specimen from the vessel. The blood smear preparation apparatus 20 controls the robotic arm to move to the blank glass slide at the operation position, and controls the pipette control apparatus of the sampling mechanism 21 to squeeze the gas in the pipette, thereby controlling the blood specimen in the pipette to flow out of the pipette onto the blank glass slide. The blood smear preparation apparatus 20 controls the gripping apparatus to grip the push slide, and place the push slide obliquely at one end of the blank glass slide to contact the blood specimen on the blank glass slide. The blood smear preparation apparatus 20 controls the gripping apparatus to move the push slide from one end of the blank glass slide to the other end to form a blood film on the blank glass slide. After the blood film is completely dried in the air, the blood smear preparation apparatus 20 controls the staining solution pipette to suck the staining solution and drop onto the blood film. After fixing for a period of time (for example, 0.5-1.0 minute), the blood smear preparation apparatus 20 controls the buffer solution pipette to suck the buffer solution. After the buffer solution is mixed with the staining solution homogenously for staining for a period of time (for example, 5-10 minutes), the blood smear preparation apparatus 20 controls the distilled water pipette to suck the distilled water to wash the staining solution on the glass slide, and after drying naturally, the prepared blood smear can be obtained. The blood smear can be automatically prepared and the blood smear preparation efficiency can be improved by the blood smear preparation apparatus in the embodiments of the present disclosure.

Optionally, that the processor 15 acquires the cell image of the blood specimen includes the processor 15 acquires at least two cell images of the (same) blood specimen (which may be acquired simultaneously or sequentially). Subsequently, when the processor automatically identifies the number of target cells and the number of reference cells in the cell image, it may automatically identify (simultaneously or sequentially) the number of target cells and the number of reference cells in the at least two cell images. It may superimpose the number of target cells in each of the at least two cell images to obtain the number of target cells in the at least two cell images, and it may superimpose the number of reference cells in each of the at least two cell images to obtain the number of reference cells in the at least two cell images. Alternatively, the at least two cell images may be spliced into one cell image before being identified. That is, the processor automatically identifies the number of target cells and reference cells in the spliced cell image.

The regions included in the at least two pictures may overlap or not, which is not limited in the embodiments of the present disclosure. When they overlap, the overlapping part needs to be removed during splicing to avoid repeated counting.

Optionally, the blood specimen is prepared into a blood smear, and that the processor 15 acquires a cell image of the blood specimen photographed by the imaging apparatus 13 is specifically as follows.

The processor 15 acquires a cell image of the specific region of the blood smear photographed by the imaging apparatus 13. The specific region includes at least one of a body-tail junction region, a body region, an edge region at either side, or a tail region of the blood smear.

The body-tail junction region of the blood smear is a better region for observing the morphology of blood cells. The specific region may also be a cell monolayer region of the blood smear. When the imaging apparatus 13 photographs the prepared blood smear, it may automatically photograph a cell image of a certain area of the specific region of the blood smear, for example, the monolayer region of the reference cells of the blood smear, and ensure that the reference cells included in the photographed area reach the preset number threshold. The greater the number of reference cells in the cell image, the greater the reference significance of the reference cells, and the higher the accuracy of the number of target cells in the blood sample to be tested can be obtained by subsequent calculation. The preset number threshold may be set in advance and stored in a memory (for example, a nonvolatile memory) of the cell image analysis apparatus 10. For example, the preset number threshold may be 1000.

Optionally, the blood specimen is prepared into a blood smear. That the processor 15 acquires a cell image of the blood specimen photographed by the imaging apparatus 13 is specifically as follows.

The processor 15 acquires at least two cell pictures of the specific region of the blood smear photographed by the imaging apparatus 13. The specific region includes at least one of a body-tail junction region, a body region, an edge region at either side, or a tail region of the blood smear.

The processor 15 combines the above at least two cell pictures into a cell image, and the cell image includes the at least two cell pictures or the cell image is formed by splicing the at least two cell pictures.

In the embodiments of the present disclosure, when the number of reference cells included in the cell picture of a specific region of the blood smear photographed by the imaging apparatus 13 is small, the imaging apparatus 13 may be controlled to photograph at least two cell pictures of the specific region of the blood smear, and the at least two cell pictures are combined into a cell image. In this way, it can be ensured that the number of reference cells included in the cell image can reach a preset number threshold, thereby improving the accuracy of the number of target cells in the blood sample to be tested obtained by subsequent calculation.

Combining the at least two cell pictures into a cell image may include the at least two cell pictures are considered as a whole, that is, as the cell image, and the cell image includes the at least two cell pictures. In this case, the at least two cell pictures are not subjected to any processing. When the cell image analysis apparatus automatically identifies the number of target cells and the number of reference cells in the cell image subsequently, it may automatically identify the number of target cells and the number of reference cells in the at least two cell pictures respectively, and it may superimpose the numbers of target cells in the at least two cell pictures to obtain the number of target cells in the cell image, and it may superimpose the numbers of reference cells in the at least two cell pictures to obtain the number of reference cells in the cell image. Combining the at least two cell pictures into a cell image may further include the at least two cell pictures are spliced into one cell image.

The regions included in the at least two pictures may overlap or not, which is not limited in the embodiments of the present disclosure. When they overlap, the overlapping part needs to be removed during splicing to avoid repeated counting.

Optionally, the at least two pictures (which may be directly used as the cell image) acquired may also be cell images of a blood specimen input by other devices or users and received by the processor, as described above, which is not limited herein.

Optionally, after the processor 15 is configured to automatically identify the number of target cells and the number of reference cells in the cell image, the processor 15 is further configured as follows.

The processor 15 is configured to perform the step of acquiring the number of reference cells in the blood sample to be tested, and calculating the number of target cells in the blood sample to be tested based on the number of target cells and the number of reference cells in the cell image and the number of reference cells in the blood sample to be tested, in the case where the number of reference cells is greater than or equal to a first threshold.

In the embodiments of the present disclosure, when the sum of the numbers of reference cells in the at least two cell images of the blood specimen acquired by the processor is greater than or equal to the first threshold, or the number of reference cells in the cell image of a specific region of the blood smear photographed by the imaging apparatus 13 is greater than or equal to the first threshold, or the number of reference cells in the cell image formed by combining at least two cell pictures of a specific region of the blood smear photographed by the imaging apparatus 13 is greater than or equal to the first threshold, it is considered that the number of reference cells included in the cell image meets the accuracy requirements for subsequent calculations, and the next step may be performed.

Optionally, after the processor 15 is configured to automatically identify the number of target cells and the number of reference cells in the cell image, the processor 15 is further configured as follows.

The processor 15 is configured to continue to perform the step of acquiring a cell image of a blood specimen, in the case where the number of reference cells is less than the first threshold.

In the embodiments of the present disclosure, when the number of reference cells is less than the first threshold, it indicates that the number of reference cells in the current cell image cannot meet the accuracy requirements of subsequent calculations, and then cell images are further acquired to be analyzed.

The first threshold may be set in advance and stored in a memory (for example, a nonvolatile memory) of the cell image analysis apparatus 10. For example, the first threshold may be 1000. The first threshold may be the same as or different from the preset number threshold, which is not limited in the embodiments of the present disclosure.

Optionally, after the processor 15 is configured to automatically identify the number of target cells and the number of reference cells in the cell image, the processor 15 is further configured as follows.

The processor 15 is configured to determine whether the sum of the numbers of reference cells in all cell images of the blood specimen acquired in history is greater than or equal to a second threshold.

That the processor 15 acquires the number of reference cells in the blood sample to be tested, and calculates the number of target cells in the blood sample to be tested based on the number of target cells and the number of reference cells in the cell image and the number of reference cells in the blood sample to be tested, is specifically as follows.

The processor 15 acquires the number of reference cells in the blood sample to be tested, and calculates the number of target cells in the blood sample to be tested based on the sum of the numbers of reference cells in all cell images of the blood specimen, the sum of the numbers of target cells in all cell images of the blood specimen, and the number of reference cells in the blood sample to be tested, in the case where the sum of the numbers of reference cells in all cell images of the blood specimen acquired in history is greater than or equal to the second threshold.

Optionally, after the processor 15 is configured to determine whether the sum of the numbers of the reference cell of all the cell images of the blood specimen acquired in history is greater than or equal to the second threshold, the processor 15 is further configured as follows.

The processor 15 is configured to continue to perform the step of acquiring the cell image of the blood specimen, in the case where the sum of the numbers of the reference cells of all the cell images of the blood specimen acquired in history is less than the second threshold.

In the embodiments of the present disclosure, for the same blood specimen, after the processor 15 analyzes the cell image of the blood specimen each time, when it is determined that the sum of the numbers of the reference cells of all the cell images of the blood specimen is less than the second threshold, the processor 15 may continue to acquire a cell image of the blood specimen; when it is determined that the sum of the numbers of the reference cells in all cell images of the blood specimen is greater than the second threshold, the processor 15 may acquire the number of reference cells in the blood sample to be tested, and calculate the number of target cells in the blood sample to be tested based on the sum of the numbers of reference cells in all cell images of the blood specimen, the sum of the numbers of target cells in all cell images of the blood specimen, and the number of reference cells in the blood sample to be tested.

The blood analyzer is further configured to detect the number of target cells in the blood sample to be tested, independent of the cell image analysis apparatus.

The system may further comprise a display apparatus, and the display apparatus is configured to display at least one of the number of target cells in the blood sample to be tested calculated by the cell image analysis apparatus, or the number of target cells in the blood sample to be tested detected by the blood analyzer.

The display apparatus is configured to display the number of target cells in the blood sample to be tested detected by the blood analyzer, when the number of reference cells in all cell images of the blood specimen acquired by the processor of the cell image analysis apparatus is less than the second threshold. As described in the above, the greater the number of reference cells in the cell image, the greater the reference significance of the reference cells, and the higher the accuracy of the number of target cells in the blood sample to be tested can be obtained by subsequent calculation. If the processor of the cell image analysis apparatus acquires the number of reference cells from the cell image of the blood specimen which is greater than or equal to the second threshold, the accuracy of the number of target cells in the blood sample calculated will be high. If the number of reference cells in all cell images of the blood specimen acquired by the processor of the cell image analysis apparatus is less than the second threshold, the display apparatus may display the number of target cells in the blood sample to be tested detected by the blood analyzer.

As example is shown as follows. The second threshold is set as 1000. The processor 15 analyzes for the first time the first cell image of the blood specimen photographed. The number of reference cells in the first cell image obtained is 100. Since the number of reference cells in the first cell image is less than the second threshold, the processor 15 analyzes for the second time the second cell image of the blood specimen photographed. The number of reference cells in the second cell image obtained is 200. Since the sum (i.e., 300) of the number of reference cells in the first cell image and the number of reference cells in the second cell image is still less than the second threshold, the processor 15 analyzes for the third time the third cell image of the blood specimen photographed. The number of reference cells in the third cell image obtained is 300. Since the sum (i.e., 600) of the number of reference cells in the first cell image, the number of reference cells in the second cell image, and the number of reference cells in the third cell image is still less than the second threshold, the processor 15 analyzes for the fourth time the fourth cell image of the blood specimen photographed. The number of reference cells in the fourth cell image obtained is 400. Since the sum (i.e., 1000) of the number of reference cells in the first cell image, the number of reference cells in the second cell image, the number of reference cells in the third cell image and the number of reference cells in the fourth cell image is equal to the second threshold, the processor 15 acquires the number of reference cells in the blood sample to be tested, and calculates the number of target cells in the blood sample to be tested based on the sum of the numbers of reference cells in all cell images of the blood specimen, the sum of the numbers of target cells in all cell images of the blood specimen, and the number of reference cells in the blood sample to be tested.

The second threshold may be set in advance and stored in a memory (for example, a nonvolatile memory) of the cell image analysis apparatus 10. For example, the second threshold may be set as 1000. The first threshold may be the same as or different from the second threshold, which is not limited in the embodiments of the present disclosure.

Optionally, the processor may also simultaneously acquire at least two cell images of the blood specimen, automatically identify the at least two cell images of the blood specimen, and obtain the number (sum) of the reference cells and/or the number (sum) of the target cells in the at least two cell images, and then determine whether the number (sum) of the reference cells obtained in the cell images of the blood specimen is greater than or equal to the first threshold (or the second threshold). For subsequent steps, reference may be made to those described above.

In the embodiments of the present disclosure, a communication connection is established between the cell image analysis apparatus 10 and the blood analyzer 30. The cell image analysis apparatus 10 may automatically acquire the number of reference cells in the blood sample to be tested from the blood analyzer 30. The blood analyzer 30 may perform routine blood tests to estimate the number of reference cells in the blood sample to be tested. The cell image analysis apparatus 10 may estimate the number of target cells in the blood sample to be tested according to the number of reference cells measured by the blood analyzer 30.

Optionally, in the case where a communication connection is not established between the cell image analysis apparatus 10 and the blood analyzer 30, the cell image analysis apparatus 10 may receive the number of reference cells in the blood sample to be tested input by the user. The cell image analysis apparatus 10 may further include an inputting apparatus. The inputting apparatus may include a mouse, a keyboard, a display screen, and the like. For example, the user may input the number of reference cells in the blood sample to be tested to the cell image analysis apparatus 10 through the inputting apparatus. In addition, optionally, even if the cell image analysis apparatus 10 is in communication with the blood analyzer 30, the cell image analysis apparatus 10 may receive the number of reference cells in the blood sample to be tested input by the user, if necessary.

Optionally, as illustrated in FIG. 1B, the specimen analysis system 100 further includes a control apparatus 40 that is connected with the blood analyzer 30, the blood smear preparation apparatus 20 and the cell image analysis apparatus 10, respectively. The cell image analysis apparatus 10 may communicate with the blood smear preparation apparatus 20 through the control apparatus 40, and may also communicate with the blood analyzer 30 through the control apparatus 40. The control apparatus is configured to control a transport device to transport the blood sample to be tested from the blood analyzer to the blood smear preparation apparatus, and is further configured to control the transport device to transport the blood smear prepared by the blood smear preparation apparatus to the cell image analysis apparatus

Optionally, as illustrated in FIG. 4, the lens group 11 may include a first objective lens 3111, a second objective lens 3112 and an eyepiece 3114 (the eyepiece is optional). The first objective lens 3111 may be, for example, a 10× objective lens, and the second objective lens 3112 may be, for example, a 100× objective lens. The lens group 311 may further include a third objective lens 3113, and the third objective lens 3113 may be, for example, a 40× objective lens.

In the embodiments of the present disclosure, after the processor 15 acquires the cell image of the blood specimen, the processor 15 may identify the number of target cells and the number of reference cells in the cell image by using an image processing algorithm. The image processing algorithm may include one or more of an image segmentation algorithm and a deep neural network algorithm.

In the embodiments of the present disclosure, after the number of target cells and the number of reference cells in the cell image and the number of reference cells in the blood sample to be tested are acquired, the ratio of the number of target cells to the number of reference cells in the cell image can be obtained, and the number of target cells in the blood sample to be tested can be obtained by multiplying the ratio of the number of target cells to the number of reference cells in the cell image by the number of reference cells in the blood sample to be tested.

In the embodiments of the present disclosure, the number of target cells in the blood sample to be tested can be accurately calculated. Compared with the manual counting method, the inspector does not need to count the target cells under the microscope for a long time, the counting efficiency of the target cells is improved, while manual errors are avoided.

With reference to FIG. 5, FIG. 5 illustrates a schematic flowchart of a target cell statistical method disclosed in an embodiment of the present disclosure. The method illustrated in FIG. 5 may be applied to the cell image analysis apparatus in the specimen analysis system illustrated in FIG. 1. The method includes the following steps.

In 501, a cell image of a blood specimen is acquired by a cell image analysis apparatus. The blood specimen is derived from a blood sample to be tested.

In the embodiments of the present disclosure, in the case where the cell image analysis apparatus does not have a photographing function, or the photographing apparatus of the cell image analysis apparatus is damaged and cannot be operated, the cell image analysis apparatus may receive the cell image of the blood specimen input from other devices through an I/O interface (for example, a USB interface). The cell image of the blood specimen may be pre-stored by other devices, or may be photographed by other devices. The cell image analysis apparatus may also receive the cell image of the blood specimen sent by the server through the communication interface. The cell image analysis apparatus may also receive the cell image of the blood specimen input by the user.

In the case where the cell image analysis apparatus has a photographing function, the cell image analysis apparatus may also receive the cell image of the blood specimen photographed by the photographing apparatus.

The blood sample to be tested is a blood sample which needs to be tested, and the blood specimen is a small amount of the blood sample to be tested and is taken from the blood sample to be tested. For example, the blood sample to be tested is 5 ml of blood. The blood specimen may be then 0.05 ml of blood. The blood specimen may be loaded on the glass slide and presented as a blood smear. For details of the preparation of the blood smear, reference may be made to the system embodiment illustrated in FIG. 1, which will not be repeated herein.

In 502, a number of target cells and a number of reference cells in the cell image are automatically identified by the cell image analysis apparatus.

In the embodiments of the present disclosure, the target cells and reference cells are different blood cells. For example, when the target cells are blood platelets, the reference cells may include one of red blood cells, white blood cells, or a combination of red blood cells and white blood cells. When the target cells are red blood cells, the reference cells may include one of white blood cells, blood platelets, or a combination of white blood cells and blood platelets. When the target cells are white blood cells, the reference cells may include one of red blood cells, blood platelets, or a combination of red blood cells and blood platelets.

Optionally, step 502 may specifically include the following step.

The cell image analysis apparatus identifies blood platelets and the reference cells in the cell image, and counts a number of blood platelets and the number of reference cells, by using an image processing method.

The image processing method may include an image segmentation method or a deep learning method.

In 503, a number of reference cells in the blood sample to be tested is acquired, and a number of target cells in the blood sample to be tested is calculated based on the number of target cells and the number of reference cells in the cell image and the number of reference cells in the blood sample to be tested, by the cell image analysis apparatus.

In the embodiments of the present disclosure, in the case where a communication connection is established between the cell image analysis apparatus and the blood analyzer, the cell image analysis apparatus may automatically acquire the number of reference cells in the blood sample to be tested from the blood analyzer. The cell image analysis apparatus may also receive the number of reference cells in the blood sample to be tested input by the user, such as in the case where a communication connection is not established between the cell image analysis apparatus and the blood analyzer. In addition, optionally, even if there is a communication connection between the two, the cell image analysis apparatus may receive the number of reference cells in the blood sample to be tested which is input by the user.

The blood analyzer may detect the blood sample to be tested to obtain the detection result of reference cells in the blood sample to be tested. The detection result of reference cells may include the total number of reference cells, the number of reference cells per milliliter of blood, and the like. For example, the blood analyzer may print out the cell detection result or display it through the display apparatus of the blood analyzer. The user may input the number of reference cells (for example, the concentration) shown in the printed cell detection result or the cell detection result displayed by the display apparatus into the cell image analysis apparatus. The user may input the total number of reference cells to the cell image analysis apparatus through an I/O interface (for example, a USB interface). Specifically, the cell image analysis apparatus may be connected with a keyboard, a mouse through an I/O interface (for example, a USB interface), and the user inputs the total number of reference cells to the cell image analysis apparatus through the keyboard and the mouse.

When the cell image analysis apparatus acquires the number of target cells and the number of reference cells in the cell image, and the number of reference cells in the blood sample to be tested, the ratio of the number of target cells to the number of reference cells in the cell image may be obtained, and the number of target cells in the blood sample to be tested may be obtained by multiplying the ratio of the number of target cells to the number of reference cells in the cell image by the number of reference cells in the blood sample to be tested.

Optionally, after step 502 is performed and before step 503 is performed, the following steps may also be performed.

The cell image analysis apparatus determines whether the number of target cells in the cell image exceeds a first preset number threshold.

If it exceeds the first preset number threshold, step 503 is performed.

If it does not exceed the first preset number threshold, step 501 to step 502 are further performed until the number of target cells cumulatively counted by the cell image analysis apparatus for a plurality of times exceeds the first preset number threshold, and then step 503 is performed.

The first preset number threshold may be preset and stored in the nonvolatile memory of the cell image analysis apparatus. For example, the first preset number threshold may be set as 1000. In the embodiments of the present disclosure, the number of reference cells in a plurality of cell images of a blood specimen may be cumulatively counted, thereby improving statistical accuracy and avoiding large statistical errors.

Step 503 includes: the cell image analysis apparatus acquires the number of reference cells in the blood sample to be tested, and calculates the number of target cells in the blood sample to be tested based on the number of target cells cumulatively counted for a plurality of times and the number of reference cells cumulatively counted for a plurality of times, and the number of reference cells in the blood sample to be tested.

The number of target cells in the blood sample to be tested may be calculated according to the following formula:

N

P
⁢
L
⁢
T

=

M

P
⁢
L
⁢
T

M

R
⁢
F
⁢
B
⁢
C

⁢

•
⁢

N

R
⁢
F
⁢
B
⁢
C

In the formula, N_PLTis the number of target cells in the blood sample to be tested, N_RFBCis the number of reference cells in the blood sample to be tested, M_PLTis the number of target cells cumulatively counted for a plurality of times, and M_RFBCis the number of reference cells cumulatively counted for a plurality of times.

Optionally, after step 502 is performed and before step 503 is performed, the following steps may also be performed.

The cell image analysis apparatus determines whether the number of target cells in the cell image exceeds a first preset number threshold.

If it exceeds the first preset number threshold, step 503 is performed.

If it does not exceed the first preset number threshold, step 501 to step 502 are further performed until the number of target cells counted by the cell image analysis apparatus exceeds the first preset number threshold, and then step 503 is performed.

Optionally, the cell image analysis apparatus displays the number of target cells in the blood sample to be tested.

Optionally, the cell image analysis apparatus transmits the number of target cells in the blood sample to be tested to other devices for display.

After the cell image analysis apparatus calculates the number of target cells in the blood sample to be tested, the number of target cells in the blood sample to be tested may be displayed on the display apparatus of the cell image analysis apparatus, or the number of target cells in the blood sample to be tested which is obtained by calculation may be displayed on other devices that communicate with the cell image analysis apparatus and have a display function, which is not limited in the embodiments of the present disclosure.

Optionally, the other devices include at least one of the blood analyzer, the blood smear preparation apparatus, or the terminal device shown in FIG. 1A or FIG. 1B.

In the embodiments of the present disclosure, the number of target cells in the blood sample to be tested can be accurately calculated. Compared with the manual counting method, the inspector does not need to count the target cells under the microscope for a long time, the counting efficiency of the target cells is improved, while manual errors are avoided.

With reference to FIG. 6, FIG. 6 illustrates a schematic flowchart of another target cell statistical method disclosed in an embodiment of the present disclosure. FIG. 6 is obtained by further optimization on the basis of FIG. 5. The method illustrated in FIG. 6 may be applied to the cell image analysis apparatus in the specimen analysis system illustrated in FIG. 1. The method includes the following steps.

In 601, a cell image of a blood specimen is acquired by a cell image analysis apparatus. The blood specimen is derived from a blood sample to be tested.

As for the specific implementation of step 601, step 501 illustrated in FIG. 5 may be referred to, which will not be repeated herein.

In 602, a cell region in the cell image is identified based on a characteristic difference between cells and a background in the cell image by the cell image analysis apparatus using an image processing method.

The image processing method may include an image segmentation method.

In the embodiments of the present disclosure, the characteristic difference between the cells and the background in the cell image may include the grayscale difference, the difference in the component of specific color space. The specific color space may comprise hue saturation intensity (HSI) color space, hue saturation value (HSV) color space, and red green blue (RGB) color space etc. For example, the cell region and the background region in the cell image may be determined according to the grayscale histogram of the cell image.