Method and device for acquiring red blood cell information using image of blood smear slide

Abstract

Provided are a method and a device, the method comprising the steps of: acquiring a plurality of patch images of a blood smear slide; acquiring cell information regarding one or more cells included in each of the plurality of patch images; acquiring feature information for the plurality of patch images on the basis of the cell information; acquiring red blood cell information for the blood smear slide on the basis of the feature information; providing the red blood cell information; performing staining on the blood smear slide; and performing analysis using the stained blood smear slide.

Description

Method and device for obtaining red blood cell information using an image of a blood smear slide

[0001] The present disclosure relates to a blood analysis method, and more particularly, to a method and device for obtaining red blood cell information using an image of a blood smear slide.

[0002] A Complete Blood Count (CBC) test analyzes information about the cellular components of blood. While CBC tests are typically performed using automated equipment, visual evaluation of a peripheral blood smear may be necessary if cellular abnormalities are detected. In some situations, rapid testing using a small amount of blood is required.

[0003] Furthermore, with recent advancements in artificial intelligence, it is being used across industries. However, developing AI models to solve problems using AI requires significant time and resources.

[0004] Embodiments of the present disclosure aim to obtain red blood cell information independently of staining of blood cells using images of blood smear slides.

[0005] In one embodiment of the present disclosure, a method for obtaining red blood cell information using an image of a blood smear slide is provided. The method may include obtaining a plurality of patch images of the blood smear slide. The method may include obtaining cell information regarding one or more cells included in each of the plurality of patch images. The method may include obtaining feature information for the plurality of patch images based on the cell information. The method may include obtaining red blood cell information for the blood smear slide based on the feature information. The method may include providing the red blood cell information. The method may include performing a staining on the blood smear slide. The method may include performing an analysis using the stained blood smear slide.

[0006] In one embodiment of the present disclosure, the step of acquiring a plurality of patch images may include the step of identifying a plurality of photographed regions on a blood smear slide. The step of acquiring a plurality of patch images may include the step of acquiring a plurality of patch images corresponding to each of the plurality of photographed regions by photographing the plurality of photographed regions.

[0007] In one embodiment of the present disclosure, the plurality of photographing regions may be a portion of a blood smear slide determined along the longitudinal direction of the blood smear slide.

[0008] In one embodiment of the present disclosure, the step of obtaining cell information regarding one or more cells included in each of the plurality of patch images may include the step of inputting each of the plurality of patch images into a classification model to obtain cell information for each patch image. The cell information may include information regarding at least one of the position, size, or shape of each cell included in each of the patch images.

[0009] In one embodiment of the present disclosure, feature information for a plurality of patch images may include at least one of first feature information, second feature information, third feature information, fourth feature information, fifth feature information, and sixth feature information for each patch image. The first feature information may include information regarding the number of cells included in each patch image. The second feature information may include information regarding a Voronoi area associated with a cell included in each patch image. The third feature information may include information regarding a distance between cells included in each patch image. The fourth feature information may include information regarding a distance from a plurality of predetermined points in each patch image to a closest cell. The fifth feature information may include information regarding a size of a cell included in each patch image. The sixth feature information may include information regarding an area ratio of a cell included in each patch image.

[0010] In one embodiment of the present disclosure, the feature information for the plurality of patch images may include at least one of seventh feature information, eighth feature information, and ninth feature information for each patch image. The seventh feature information may include information related to the value of a color component included in each patch image. The eighth feature information may include information related to a shooting area for each patch image. The ninth feature information may include information related to the number of red blood cells included in each patch image.

[0011] In one embodiment of the present disclosure, the red blood cell information may include at least one of a hemoglobin level and a hematocrit level for blood included in a blood smear slide. The step of providing the red blood cell information may include a step of outputting the hemoglobin level, evaluation information for the hemoglobin level, the hematocrit level, and evaluation information for the hematocrit level through a display.

[0012] In one embodiment of the present disclosure, the step of obtaining red blood cell information for a blood smear slide based on feature information may include the step of obtaining red blood cell information by inputting the feature information into an artificial intelligence model. The artificial intelligence model may be trained using feature information determined based on training images of unstained cells and red blood cell information corresponding to the training images.

[0013] In one embodiment of the present disclosure, the step of staining a blood smear slide may include the step of staining for a CBC test. The step of performing an analysis using the stained blood smear slide may include the step of determining at least one of the number of blood cells contained in the blood and the white blood cell differential count.

[0014] In one embodiment of the present disclosure, the step of staining a blood smear slide may include a step of determining a staining area based on a plurality of patch images. The step of staining the blood smear slide may include a step of fixing the blood smear slide. The step of staining the blood smear slide may include a step of staining a staining area of ​​the blood smear slide.

[0015] In one embodiment of the present disclosure, a device for classifying cells included in an image is provided. The device may include a memory comprising one or more instructions and at least one processor. The at least one processor may execute one or more instructions, thereby allowing the device to obtain multiple patch images of a blood smear slide. The at least one processor may execute one or more instructions, thereby allowing the device to obtain cell information regarding one or more cells included in each of the multiple patch images. The at least one processor may execute one or more instructions, thereby allowing the device to obtain feature information for the multiple patch images based on the cell information. The at least one processor may execute one or more instructions, thereby allowing the device to obtain red blood cell information for the blood smear slide based on the feature information. The at least one processor may execute one or more instructions, thereby allowing the device to provide red blood cell information. The at least one processor may execute one or more instructions, thereby allowing the device to stain the blood smear slide. The at least one processor may execute one or more instructions, thereby allowing the device to perform analysis using the stained blood smear slide.

[0016] In one embodiment of the present disclosure, at least one processor executes one or more instructions, thereby enabling the device to identify multiple capture regions on a blood smear slide. At least one processor executes one or more instructions, thereby enabling the device to capture multiple capture regions, thereby obtaining multiple patch images corresponding to each of the multiple capture regions.

[0017] In one embodiment of the present disclosure, the plurality of photographing regions may be a portion of a blood smear slide determined along the longitudinal direction of the blood smear slide.

[0018] In one embodiment of the present disclosure, at least one processor executes one or more instructions, thereby causing the device to input each of a plurality of patch images into a classification model to obtain cell information for each patch image. The cell information may include information regarding at least one of the position, size, or shape of each cell included in each patch image.

[0019] In one embodiment of the present disclosure, feature information for a plurality of patch images may include at least one of first feature information, second feature information, third feature information, fourth feature information, fifth feature information, and sixth feature information for each patch image. The first feature information may include information regarding the number of cells included in each patch image. The second feature information may include information regarding a Voronoi area associated with a cell included in each patch image. The third feature information may include information regarding a distance between cells included in each patch image. The fourth feature information may include information regarding a distance from a plurality of predetermined points in each patch image to a closest cell. The fifth feature information may include information regarding a size of a cell included in each patch image. The sixth feature information may include information regarding an area ratio of a cell included in each patch image.

[0020] In one embodiment of the present disclosure, the feature information for the plurality of patch images may include at least one of seventh feature information, eighth feature information, and ninth feature information for each patch image. The seventh feature information may include information related to the value of a color component included in each patch image. The eighth feature information may include information related to a shooting area for each patch image. The ninth feature information may include information related to the number of red blood cells included in each patch image.

[0021] In one embodiment of the present disclosure, the red blood cell information may include at least one of a hemoglobin level and a hematocrit level for blood contained in a blood smear slide. At least one processor may execute one or more instructions, thereby causing the device to output the hemoglobin level, evaluation information for the hemoglobin level, hematocrit level, and evaluation information for the hematocrit level through a display.

[0022] In one embodiment of the present disclosure, at least one processor executes one or more instructions, thereby causing the device to acquire red blood cell information by inputting feature information into an artificial intelligence model. The artificial intelligence model may be trained using feature information determined based on training images of unstained cells and red blood cell information corresponding to the training images.

[0023] In one embodiment of the present disclosure, at least one processor may execute one or more instructions to cause the device to perform staining for a CBC test. At least one processor may execute one or more instructions to cause the device to determine at least one of the number of blood cells contained in blood and the white blood cell differential count.

[0024] In one embodiment of the present disclosure, at least one processor executes one or more instructions, thereby enabling the device to determine a staining region based on a plurality of patch images. At least one processor executes one or more instructions, thereby enabling the device to perform fixation on a blood smear slide. At least one processor executes one or more instructions, thereby enabling the device to perform staining on a staining region of a blood smear slide.

[0025] In one embodiment of the present disclosure, a computer-readable recording medium having recorded thereon a program for performing the above-described method on a computer is provided.

[0026] In one embodiment of the present disclosure, CBC and blood smear tests can be performed simultaneously, reducing testing time and increasing efficiency, enabling rapid diagnostic results for patients. Analysis can be performed using blood smear slide images without separate staining, resulting in cost savings. Furthermore, high correlation with existing automated blood analyzers can be maintained.

[0027] The effects of the embodiments of the present disclosure are not limited to the effects described above, and effects not mentioned can be clearly understood by a person having ordinary skill in the art to which the present invention pertains from this specification and the attached drawings.

[0028] FIG. 1 is a drawing for explaining a device for obtaining red blood cell information using an image of a blood smear slide according to one embodiment of the present disclosure.

[0029] FIG. 2 is a flowchart of a method for processing a sample by a device according to one embodiment of the present disclosure.

[0030] FIG. 3 is a flowchart of a method for obtaining red blood cell information using an image of a blood smear slide in one embodiment of the present disclosure.

[0031] FIG. 4 is a drawing for explaining a patch image for a blood smear slide according to one embodiment of the present disclosure.

[0032] FIG. 5 is a block diagram of a device for obtaining red blood cell information using an image of a blood smear slide, according to one embodiment of the present disclosure.

[0033] FIG. 6 is a diagram showing a UI of a display providing red blood cell information according to one embodiment of the present disclosure.

[0034] FIG. 7 is a diagram showing multiple patch images for a blood smear slide according to one embodiment of the present disclosure.

[0035] FIG. 8 is a drawing for explaining a blood smear slide on which staining has been performed, in one embodiment of the present disclosure.

[0036] FIG. 9 is a flowchart of a method for determining an analysis area of ​​a blood smear slide on which staining has been performed, in one embodiment of the present disclosure.

[0037] FIG. 10 is a block diagram illustrating a device for obtaining red blood cell information using an image of a blood smear slide according to one embodiment of the present disclosure.

[0038] FIG. 11 is a block diagram illustrating a device for obtaining red blood cell information using an image of a blood smear slide according to one embodiment of the present disclosure.

[0039] The terms used in this disclosure will be briefly explained, and one embodiment of the present disclosure will be specifically described.

[0040] The terms used in this disclosure are selected from widely used, current terms, taking into account the functions of one embodiment of the disclosure. However, these terms may vary depending on the intentions of those skilled in the art, precedents, the emergence of new technologies, etc. Furthermore, in certain cases, terms may be arbitrarily selected by the applicant, and in such cases, their meanings will be described in detail in the description of the relevant embodiments of the disclosure. Therefore, the terms used in this disclosure should not be defined simply as names of terms, but rather based on the meanings of the terms and the overall content of the disclosure.

[0041] Throughout this disclosure, when a part is said to "include" a certain component, this does not mean that other components are excluded, but rather that other components may be included, unless otherwise specifically stated. Furthermore, terms such as "part," "module," etc., used in this disclosure refer to a unit that processes at least one function or operation, which may be implemented in hardware or software, or a combination of hardware and software.

[0042] In this disclosure, when an element or layer is referred to as being “on” or “on” another element or layer, it may include not only directly on top of the other element or layer, but also intervening layers or other components.

[0043] In the present disclosure, “at least one of a, b, or c” may include “a,” “b,” “c,” “a and b,” “b and c,” “a and c,” and “a, b, and c.” Additionally, the expression “at least one of a, b, or c” may be replaced by the term “and / or,” such as “a, b, and / or c.”

[0044] Below, with reference to the attached drawings, embodiments of the present disclosure are described in detail so that those skilled in the art can easily implement the present disclosure. However, one embodiment of the present disclosure may be implemented in various different forms and is not limited to the embodiments described herein. In addition, in the drawings, parts irrelevant to the description are omitted to clearly describe one embodiment of the present disclosure, and similar parts are designated with similar drawing reference numerals throughout the present disclosure.

[0045] FIG. 1 is a drawing for explaining a device for obtaining red blood cell information using an image of a blood smear slide according to one embodiment of the present disclosure.

[0046] In one embodiment of the present disclosure, the device (2000) can acquire a patch image (110) for a blood smear slide (100). For example, when a cartridge containing a blood smear slide (100) is inserted into the device (2000), the device (2000) can acquire a patch image (110) by photographing the blood smear slide (100). In one embodiment of the present disclosure, the blood smear slide (100) can include unstained cells (e.g., blood cells). The device (2000) can acquire a plurality of patch images (110) in which unstained cells are photographed by photographing a plurality of areas of the blood smear slide (100).

[0047] In one embodiment of the present disclosure, the device (2000) can analyze cells included in a patch image (110). For example, the device (2000) can identify cells included in the patch image (110). The device (2000) can obtain cell information about the patch image. For example, the device (2000) can include information about the size, position, and / or shape of cells included in the patch image. For example, referring to FIG. 1, the cell image (120) can be an image representing cell information about the size, position, and / or shape of cells included in the patch image (110). The cell image (120) can include one or more cells and a bounding box representing each cell (e.g., a boundary area expressed to be adjacent to a cell). For example, a square displayed in the cell image (120) can represent a bounding box. However, the present invention is not limited thereto, and the cell information can include a cell boundary determined on a pixel basis instead of a square bounding box.

[0048] In one embodiment of the present disclosure, the device (2000) may obtain red blood cell information based on cell information. For example, the device (2000) may obtain feature information based on the cell information, and obtain red blood cell information based on the feature information. The red blood cell information may refer to information related to red blood cells in blood included in a blood smear slide. For example, the red blood cell information may include the hematocrit value or hemoglobin value of blood included in a blood smear slide.

[0049] In one embodiment of the present disclosure, the device (2000) can process blood on a blood smear slide (100). For example, the device (2000) can perform smear processing, fixation processing, and staining processing on a cartridge. The cartridge processing process is automatically performed by the device (2000). For example, the series of processes in which a sample is smeared, fixed, and stained does not require manual intervention by a human and can be automatically performed by the device (2000). In a conventional blood smear test, the processes of smearing, staining, and microscopic observation of blood depend on the manual work of the examiner. Therefore, if the examiner is not skilled, the blood smear condition may become uneven, or the sample may be contaminated due to errors in reaction conditions during the blood staining process, making it difficult to perform the examination. In addition, if the examiner lacks skill, accurate examination is difficult. In addition, since the examiner must visually classify cells, it requires a lot of time and money. However, the device (2000) according to one embodiment of the present disclosure can automatically perform the blood smear and staining process, and can provide fast and accurate analysis results regardless of the skill of the examiner through image processing using artificial intelligence.

[0050] In one embodiment of the present disclosure, the device (2000) can provide red blood cell information. For example, the device (2000) can provide red blood cell information to a user (130) through a display. For example, the device (2000) can transmit the red blood cell information to a server (140). The device (2000) can provide the red blood cell information to an external device through the server (140).

[0051] FIG. 2 is a flowchart of a method for processing a sample by a device according to one embodiment of the present disclosure.

[0052] In one embodiment of the present disclosure, a method for processing a specimen may be performed by a device (2000). For example, the device (2000) may perform each step of processing a specimen by having a processor of the device (2000) execute at least one instruction contained in a memory. The processor controlling the device (2000) may perform image processing and operations performed by artificial intelligence. In one embodiment, the processor may include an artificial intelligence processor. In one embodiment, the processor may include multiple processors.

[0053] In step S210, the device (2000) may obtain a cartridge containing a specimen (e.g., blood or tissue). The cartridge may include a contact staining patch containing a staining sample and a specimen area where the specimen is smeared. For example, the cartridge may have the contact staining patch positioned above the specimen area where the specimen is smeared.

[0054] In one embodiment of the present disclosure, the device (2000) may include a loading area in which a cartridge is placed. The loading area may refer to a space in which a cartridge can be provided to the device (2000). For example, the device (2000) may obtain a cartridge through the loading area.

[0055] In step S220, the device (2000) may smear a specimen contained in the cartridge on the specimen area. In one embodiment, the device (2000) may move the patch plate of the cartridge or the specimen plate of the cartridge to smear the specimen contained in the cartridge on the specimen area. For example, the device (2000) may move at least one of the patch plate or the specimen plate to create a change in relative position. The specimen may be smeared by a contact portion included in the patch plate. For example, smearing may be performed by physically moving at least a portion of the specimen according to a change in relative position between the specimen and the contact portion caused by the device (2000). The patch plate may refer to a component (e.g., a body) of the cartridge that includes a contact staining patch, and the specimen plate may refer to a component (e.g., a body) of the cartridge that includes a specimen. The patch plate and the specimen plate may include protrusions and / or grooves for mutual coupling.

[0056] In step S230, the device (2000) may acquire red blood cell information. In one embodiment of the present disclosure, the device (2000) may acquire red blood cell information for the specimen plate. For example, the device (2000) may capture a patch image for the specimen plate and acquire red blood cell information using the captured patch image. In one embodiment of the present disclosure, the red blood cell information may include, but is not limited to, at least one of a hematocrit value and a hemoglobin value. In one embodiment of the present disclosure, the specimen plate may include a blood smear slide. In one embodiment of the present disclosure, the specimen plate may include a specimen in an unstained state. In one embodiment of the present disclosure, the process of the device (2000) acquiring red blood cell information will be described in detail with reference to FIGS. 3 to 7 .

[0057] In step S240, the device (2000) can fix a specimen. In one embodiment of the present disclosure, the patch plate may include a storage portion for fixing patches for fixing a specimen. In one embodiment of the present disclosure, the storage portion for the fixing patches may include a fixative (e.g., methanol, ethanol). The device (2000) may discharge the fixative contained in the storage portion according to a specific operation. For example, the device (2000) may induce the discharge of the fixative by applying pressure to the storage portion.

[0058] In step S250, the device (2000) can stain a specimen. In one embodiment of the present disclosure, the device (2000) can perform staining on a cartridge using a contact staining patch containing a staining sample. The staining sample may include a substance that stains the specimen. For example, the staining sample may include a staining reagent that directly stains the specimen, but is not limited thereto, and may include a substance that reacts with the staining target substance to enable detection of the staining target substance.

[0059] The device (2000) can perform staining by bringing a contact dye patch into contact with a specimen. For example, the specimen may undergo chemical bonding through contact with the contact dye patch. The device (2000) can sequentially bring a plurality of contact dye patches into contact with the specimen.

[0060] In one embodiment of the present disclosure, some of the dyed samples may not bind to the sample. For example, the sample and the dyed sample may not bind. Among the dyed samples in contact with the sample, the unreacted dyed samples that are not bound to the sample may be reabsorbed into the contact patch when the sample area and the contact patch are separated.

[0061] In step S260, the device (2000) can photograph the stained specimen. The device (2000) can photograph the stained specimen using an image inspection unit (e.g., an optical lens). The device (2000) can obtain an image that is magnified (e.g., 20x, 50x, etc.) using the image inspection unit. The degree of magnification can be determined differently depending on the purpose of the examination.

[0062] The device (2000) can acquire multiple specimen images (e.g., patch images) in the z-axis direction when the width of the cartridge is the x-axis and the height is the y-axis. That is, the device (2000) can acquire multiple images by changing the depth in the direction of the stacked single layer (vertical direction of the slide) in which the specimen is smeared. For example, the device (2000) can acquire multiple images at each depth within a range within the thickness of the specimen.

[0063] In one embodiment of the present disclosure, the device (2000) can capture multiple specimen images by sequentially capturing portions of a cartridge. For example, the device (2000) can capture a first region of the cartridge and a second region located above the first region. In one embodiment of the present disclosure, the device (2000) can perform an analysis on a stained specimen based on the specimen images.

[0064] FIG. 3 is a flowchart of a method for obtaining red blood cell information using an image of a blood smear slide in one embodiment of the present disclosure.

[0065] In one embodiment of the present disclosure, a method for obtaining red blood cell information using an image of a blood smear slide may be performed by a device (2000). For example, the device (2000) may perform each step of the method for obtaining red blood cell information by having a processor of the device (2000) execute at least one instruction contained in a memory. The processor controlling the device (2000) may perform image processing and operations performed by artificial intelligence. In one embodiment, the processor may include an artificial intelligence processor. In one embodiment, the processor may include a plurality of processors.

[0066] In step S310, the device (2000) can acquire multiple patch images for the blood smear slide. The patch images may correspond to a portion of the blood smear slide.

[0067] In one embodiment of the present disclosure, the device (2000) can acquire a patch image by photographing a portion of a blood smear slide. For example, the device (2000) can photograph the patch image along a predetermined direction of the blood smear slide. The multiple patch images may be images of different regions of the blood smear slide. In one embodiment of the present disclosure, the process of the device (2000) photographing the patch image is described with reference to FIG. 4.

[0068] In step S320, the device (2000) may obtain cell information regarding one or more cells included in each of the plurality of patch images. The patch image may include one or more cells located in an area of ​​the photographed blood smear slide.

[0069] In one embodiment of the present disclosure, the device (2000) can acquire cell information contained in each patch image by inputting each of the plurality of patch images into an artificial intelligence model. For example, the artificial intelligence model may be an artificial intelligence model trained to output cell information contained in the input image.

[0070] In one embodiment of the present disclosure, cell information may include information related to the size, location, or shape of each cell included in a patch image. In one embodiment of the present disclosure, a process by which the device (2000) acquires cell information regarding cells included in a patch image is described with reference to FIG. 5.

[0071] In step S330, the device (2000) can obtain feature information for multiple patch images based on cell information.

[0072] In one embodiment of the present disclosure, the feature information may include information regarding relationships between cells included in a patch image and / or information regarding the number or area of ​​cells included in the patch image. In one embodiment of the present disclosure, a process by which the device (2000) determines feature information based on cell information is described with reference to FIG. 5.

[0073] In step S340, the device (2000) can obtain red blood cell information for the blood smear slide based on the feature information.

[0074] In one embodiment of the present disclosure, the device (2000) can acquire red blood cell information by inputting feature information into an artificial intelligence model. The artificial intelligence model may be trained using feature information determined based on training images of unstained cells and red blood cell information corresponding to the training images. In one embodiment of the present disclosure, the process by which the device (2000) acquires red blood cell information for a blood smear slide based on feature information is described with reference to FIG. 5.

[0075] In step S350, the device (2000) may provide red blood cell information. For example, the device (2000) may provide a red blood cell count and / or information determining whether the red blood cell count is normal. In one embodiment of the present disclosure, the device (2000) may display the red blood cell information on a display or transmit it to a server or external electronic device.

[0076] In step S360, the device (2000) may perform staining on a blood smear slide. In one embodiment of the present disclosure, the device (2000) may acquire a patch image using an unstained blood smear slide and then perform staining on the blood smear slide. The device (2000) may determine a staining sample according to the analysis purpose. For example, the device (2000) may perform staining for a CBC test. In one embodiment of the present disclosure, the process of the device (2000) performing staining can be understood with reference to step S250 of FIG. 2.

[0077] In step S370, the device (2000) may perform an analysis using a stained blood smear slide. In one embodiment of the present disclosure, the device (2000) may perform an analysis on cells or tissues contained in the stained blood smear slide. For example, the device (2000) may determine at least one of the number of blood cells contained in the blood and a white blood cell differential count.

[0078] The device (2000) can determine a medical level by analyzing stained cells or stained tissue. The medical level may refer to an analysis result related to the patient's health status. For example, the medical level may include at least one of the following: whether the patient has malaria, the percentage of infected RBCs, or the type of malaria infection. For example, the medical level may include the patient's blood cell count or blood cell ratio. For example, the medical level may include the patient's cervical cancer diagnosis stage.

[0079] The device (2000) can determine the medical level depending on the purpose of the analysis. For example, if the purpose of the analysis is whether the patient is infected with malaria, the device (2000) can determine the presence of infection, the type of malaria infected, and / or the level of infection (e.g., the percentage of infected samples). For example, if the purpose of the analysis is a peripheral blood smear test, the device (2000) can determine the type classification of white blood cells (e.g., the five major types of white blood cells) and / or basic blood test parameters. Basic blood tests can include the number of blood cells (e.g., white blood cells, red blood cells, platelets) contained in the blood per unit volume, and / or a white blood cell differential count. For example, if the purpose of the analysis is a cervical analysis, the device (2000) can analyze cervical cells contained in the tissue and determine the degree of progression based on the Bethesda system, which is a cervical cancer progression scale. However, medical levels for various analysis purposes can be determined by the device (2000) without being limited to the above-mentioned analysis purposes.

[0080] In one embodiment of the present disclosure, the device (2000) can obtain red blood cell information without a separate staining process or measurement reagent. Therefore, the device (2000) can obtain red blood cell information with a short processing time and perform additional analysis through the staining process.

[0081] FIG. 4 is a drawing for explaining a patch image for a blood smear slide according to one embodiment of the present disclosure.

[0082] Referring to FIG. 4, a blood smear slide (100) according to one embodiment of the present disclosure is illustrated. The blood smear slide (100) may be after blood smearing has been performed and before staining has been performed.

[0083] In one embodiment of the present disclosure, the device (2000) can acquire multiple patch images for a blood smear slide (100). For example, the device (2000) can acquire multiple patch images by photographing a predetermined location of the blood smear slide (100).

[0084] In one embodiment of the present disclosure, the device (2000) can identify a photographing region of a blood smear slide (100). For example, the device (2000) can identify a plurality of photographing regions including a first photographing region (400-1), a second photographing region (400-2), and an n-th photographing region (400-n). The photographing regions may be a plurality of different regions of the blood smear slide (100).

[0085] In one embodiment of the present disclosure, the photographing area can be determined along a predetermined direction of the blood smear slide (100). For example, the photographing area can be determined along the width direction or the height direction of the blood smear slide (100).

[0086] In one embodiment of the present disclosure, the photographing area may be determined along the longitudinal direction of the blood smear slide (100). For example, the longitudinal direction of the blood smear slide (100) may refer to the direction in which the length is longer among the width direction or the height direction of the blood smear slide (100), but is not limited thereto.

[0087] In one embodiment of the present disclosure, the device (2000) can determine a plurality of photographing regions along a predetermined direction of a blood smear slide (100). In one embodiment of the present disclosure, each photographing region may correspond to a different region of the blood smear slide (100), but is not limited thereto, and some regions of the blood smear slide (100) may be commonly included in the plurality of photographing regions. For example, the first photographing region (400-1) and the second photographing region (400-2) may include a common region. In one embodiment of the present disclosure, each photographing region may be determined continuously, but is not limited thereto, and each photographing region may be spaced apart by a predetermined distance. For example, a predetermined distance may exist between the first photographing region (400-1) and the second photographing region (400-2).

[0088] In one embodiment of the present disclosure, the device (2000) can acquire a patch image corresponding to the photographing area by photographing the photographing area. For example, the device (2000) can acquire a patch image by photographing along a predetermined direction of a blood smear slide.

[0089] In one embodiment of the present disclosure, the device (2000) can acquire a patch image stored in memory or a patch image captured by an external device. For example, the device (2000) can receive a patch image captured by an external device via wired or wireless means.

[0090] FIG. 5 is a block diagram of a device for obtaining red blood cell information using an image of a blood smear slide, according to one embodiment of the present disclosure.

[0091] Referring to FIG. 5, the device (2000) may include an object identification module (510), a feature extraction module (520), and a red blood cell information determination module (530). The device (2000) may determine red blood cell information of a blood smear slide from a patch image.

[0092] The object identification module (510) can obtain cell information from the patch image. For example, the object identification module (510) can input each of a plurality of patch images into a classification model to obtain cell information for each patch image. In one embodiment of the present disclosure, the classification module may include an artificial intelligence model for identifying cells included in the image. For example, the classification module may include an artificial intelligence model of the object detection or segmentation type. The cell information may include the location of the cell included in the patch image, the size of the cell, and / or the shape of the cell.

[0093] In one embodiment of the present disclosure, the object identification module (510) can identify cells included in a patch image. For example, the patch image may include white blood cells, red blood cells, and / or platelets included in blood, and the object identification module (510) can identify a plurality of white blood cells, red blood cells, and / or platelets included in the patch image. Alternatively, for example, the patch image may include a plurality of white blood cells, red blood cells, and / or platelets included in blood, but the object identification module (510) can identify only the red blood cells included in the patch image.

[0094] In one embodiment of the present disclosure, the object identification module (510) can identify the location of a cell included in a patch image, the size of the cell, and / or the shape of the cell. For example, the object identification module (510) can identify the location of a red blood cell included in a patch image, the size of the red blood cell, and / or the shape of the red blood cell.

[0095] In one embodiment of the present disclosure, the feature extraction module (520) can determine feature information based on cell information. The feature extraction module (520) can determine feature information corresponding to each patch image.

[0096] In one embodiment of the present disclosure, the feature information may include information regarding the number of cells included in the patch image. The feature extraction module (520) may determine the number of cells included in the patch image. The feature extraction module (520) may determine the number of cells included in the patch image based on the cell information. For example, the feature extraction module (520) may determine the number of cells based on information regarding the location of the cells, the size of the cells, and / or the shape of the cells.

[0097] In one embodiment of the present disclosure, the feature information may include information regarding a Voronoi area associated with a cell included in a patch image. The feature extraction module (520) may determine the Voronoi area associated with a cell included in the patch image. Voronoi is a method of dividing a plane into a plurality of polygons, and may refer to a method of dividing the plane into a set of points with the closest distance to a feature point. The feature extraction module (520) may determine the location of a cell as a feature point and determine the Voronoi area. For example, the feature extraction module (520) may determine the location of all or part of an identified cell as a feature point, divide the patch image into a plurality of polygons based on the feature point, and determine the area of ​​the divided polygons. In one embodiment of the present disclosure, the feature information may include an average of the Voronoi area and / or a standard deviation of the Voronoi area.

[0098] In one embodiment of the present disclosure, the feature information may include information regarding the distance between cells included in the patch image. The feature extraction module (520) may determine the distance between cells included in the patch image. For example, the feature extraction module (520) may determine the distance between cells based on the location of the identified cells. In one embodiment of the present disclosure, the feature information may include the average distance between cells and / or the standard deviation of the distance between cells.

[0099] In one embodiment of the present disclosure, the feature information may include information regarding the distance from a plurality of predetermined points in the patch image to the nearest cell. The feature extraction module (520) may determine information regarding the distance from a plurality of predetermined points in the patch image to the nearest cell. For example, the feature extraction module (520) may determine information regarding the distance from a plurality of predetermined points in the patch image to the nearest cell based on the location of the cell. In one embodiment of the present disclosure, a plurality of predetermined points may be predetermined at equal intervals in the patch image. In one embodiment of the present disclosure, the feature information may include the average and / or standard deviation of the distances from a plurality of predetermined points in the patch image to the nearest cell.

[0100] In one embodiment of the present disclosure, the feature information may include information related to the size of cells included in the patch image. The feature extraction module (520) may determine information related to the size of cells included in the patch image. For example, the feature extraction module (520) may determine the average size or the median size of cells included in the patch image based on the sizes of the identified cells.

[0101] In one embodiment of the present disclosure, the feature information may include information regarding the area ratio of cells included in the patch image. The feature extraction module (520) may determine the area ratio of cells included in the patch image. For example, the feature extraction module (520) may determine the area ratio of cells included in the patch image based on the size of the identified cells, the shape of the cells, and / or the location of the cells. In one embodiment of the present disclosure, the information regarding the area ratio of cells may include the average and / or standard deviation of the area ratio of cells included in the patch image.

[0102] In one embodiment of the present disclosure, feature information may include information related to the values ​​of color components included in a patch image. The feature extraction module (520) may determine the values ​​of color components included in the patch image. For example, the feature extraction module (520) may obtain the values ​​of the red component, green component, and blue component of a cell included in the patch image. In one embodiment of the present disclosure, information related to the values ​​of the color components may include the average and / or median values ​​of the values ​​of the color components.

[0103] In one embodiment of the present disclosure, the feature information may include information related to the captured area for the patch image. The feature extraction module (520) may determine a value related to the captured area for the patch image. For example, the feature extraction module (520) may determine the interval at which the patch images were captured. For example, the feature extraction module (520) may determine the location of the last captured patch image.

[0104] In one embodiment of the present disclosure, the feature information may include information related to the number of red blood cells included in a patch image. The feature extraction module (520) may determine the number of red blood cells included in the patch image. The feature extraction module (520) may determine the coefficient of variation of the number of red blood cells included in a plurality of patch images. The feature extraction module (520) may determine the amount of change (e.g., a decreasing slope) in the number of red blood cells included in a plurality of patch images.

[0105] However, the aforementioned feature information is only an example, and the device (2000) may use additional feature information or omit some feature information to obtain red blood cell information.

[0106] In one embodiment of the present disclosure, the red blood cell information determination module (530) can determine red blood cell information based on feature information. In one embodiment of the present disclosure, the red blood cell information determination module (530) can include an artificial intelligence model trained to determine red blood cell information based on feature information. The artificial intelligence model can determine red blood cell information by inputting feature information for multiple patch images. For example, multiple types of feature information described above can be input into the artificial intelligence model, and red blood cell information including hematocrit values ​​and / or hemoglobin values ​​can be output.

[0107] In one embodiment of the present disclosure, an artificial intelligence model may be trained using feature information determined based on training images of unstained cells and red blood cell information corresponding to the training images. For example, the object identification module (510) may determine cell information from the training images, and the feature extraction module (520) may determine feature information from the cell information. The artificial intelligence model may be trained using feature information corresponding to the training images and red blood cell information in the training images.

[0108] In one embodiment of the present disclosure, the red blood cell information determination module (530) may perform preprocessing before inputting feature information into an artificial intelligence model. For example, the red blood cell information determination module (530) may obtain statistical information and input the statistical information into the artificial intelligence model. The statistical information may include feature information of a first patch image among a plurality of patch images and feature information of a last patch image among a plurality of patch images. The statistical information may include at least one of an average, a standard deviation, a maximum increase rate, a maximum decrease rate, a change rate, an acceleration, a slope, and a coefficient of variation for the feature information of each patch image. The statistical information may determine whether the feature information of the patch image increases or decreases. For example, whether the feature information increases or decreases may be determined by comparing the feature information of the first patch image with the feature information of the last patch image. The feature information may include one or more types of feature information obtained by the feature extraction module (520). For example, the red blood cell information determination module (530) can obtain statistical information on at least one of the number of cells in each patch image, the average of the Voronoi area, the standard deviation of the Voronoi area, the average of the spacing between cells, the standard deviation of the spacing between cells, the average size of the cells, the median of the size of the cells, the average of the area ratio of the cells, the standard deviation of the area ratio of the cells, the median of the red component, the median of the green component, and the median of the blue component.

[0109] In one embodiment of the present disclosure, the red blood cell information determination module (530) may perform the same preprocessing on each feature information of each patch image. For example, the red blood cell information determination module (530) may perform the same preprocessing on the number of cells, the average of the Voronoi area, the standard deviation of the Voronoi area, the average of the spacing between cells, the standard deviation of the spacing between cells, the average size of the cells, the median of the size of the cells, the average of the area ratio of the cells, the standard deviation of the area ratio of the cells, the median of the red component, the median of the green component, and the median of the blue component of each patch image to obtain statistical information.

[0110] FIG. 6 is a diagram showing a UI of a display providing red blood cell information according to one embodiment of the present disclosure.

[0111] Referring to FIG. 6, a UI (600) for displaying red blood cell information is illustrated on a device (2000). In one embodiment of the present disclosure, the device (2000) can provide red blood cell information through a display. The device (2000) can acquire red blood cell information using a patch image of a blood smear slide and provide the acquired red blood cell information through a display.

[0112] In one embodiment of the present disclosure, the device (2000) can display a hemoglobin level (610). For example, the device (2000) can display a hemoglobin level of 11.5 g / dL obtained using a patch image. The hemoglobin level can be determined by the weight of hemoglobin per unit dose. The device (2000) can display evaluation information (612) regarding the hemoglobin level (610). For example, the device (2000) can display whether the hemoglobin level (610) is within the normal range, or is above or below the normal range. The device (2000) can graphically display the hemoglobin level (610). For example, the device (2000) can display graphical hemoglobin level information (614). For example, the device (2000) may display hemoglobin level information (614) indicating hemoglobin level and normal range of hemoglobin level.

[0113] In one embodiment of the present disclosure, the device (2000) can display a hematocrit value (620). For example, the device (2000) can display 35.1%, which is a hematocrit value (620) obtained using a patch image. The hematocrit value (620) can refer to the percentage of red blood cells in the total blood. The device (2000) can display evaluation information (622) regarding the hematocrit value (620). For example, the device (2000) can display whether the hematocrit value (620) is within a normal range, or is higher or lower than the normal range. The device (2000) can graphically display the hematocrit value (620). For example, the device (2000) can display graphical hematocrit value information (624). For example, the device (2000) can display hematocrit value information (624) indicating the hematocrit value and the normal range of the hematocrit value.

[0114] FIG. 7 is a diagram showing multiple patch images for a blood smear slide according to one embodiment of the present disclosure.

[0115] Referring to FIG. 7, a plurality of patch images arranged according to the photographing position of a blood smear slide are illustrated. In one embodiment of the present disclosure, the device (2000) can photograph patch images corresponding to a portion of a blood smear slide. For example, the device (2000) can acquire a patch image for a photographing area.

[0116] In one embodiment of the present disclosure, the capturing area of ​​a patch image may be determined based on the longitudinal direction of the blood smear slide. For example, the capturing area (710) may be determined based on the longer direction of either the height or width of the blood smear slide. For example, the capturing area (710) may be determined at regular intervals along the longitudinal direction.

[0117] In one embodiment of the present disclosure, the imaging area may include only one set along the longitudinal direction. For example, as illustrated in FIG. 7, the left and right areas of the imaging area (710) can also be imaged for a blood smear slide, but the device (2000) can only image once along the longitudinal direction, like the imaging area (710). However, the present invention is not limited thereto, and the imaging area may include multiple sets along the longitudinal direction. For example, the imaging area may also include the imaging area (710) of FIG. 7 and areas located to the left and right of the imaging area (710).

[0118] In one embodiment of the present disclosure, the device (2000) can capture patch images for a capture area. The device (2000) can continuously capture images along a predetermined direction. While patch images can be continuously captured along the predetermined direction, the present invention is not limited thereto, and some areas may not be captured. For example, an area between a patch image (720) at a first location and a patch image (725) at a second location may not be captured.

[0119] In one embodiment of the present disclosure, the device (2000) can determine a staining region (750) based on a plurality of patch images. The device (2000) can select a target patch image (730) from among the plurality of patch images. The device (2000) can determine a region of interest (740) based on the target patch image (730). The device (2000) can determine a staining region (750) based on the region of interest (740). The target patch image (730) may refer to a patch image that serves as a reference for determining the region of interest (740) or a patch image that is most likely to be the region of interest (740). The region of interest (740) may refer to a region suitable for a blood test and may be referred to as an ideal zone.

[0120] In one embodiment of the present disclosure, the device (2000) can obtain a score corresponding to a patch image. The device (2000) can obtain a score corresponding to a patch image based on feature information. The device (2000) can input feature information for each patch image into an artificial intelligence model and obtain a score corresponding to the patch image. The artificial intelligence model may be a model trained to input feature information for each patch image and output a score for the patch image based on the input feature information. The artificial intelligence model for obtaining a score corresponding to a patch image may be a separate model from the artificial intelligence model for obtaining red blood cell information. In one embodiment of the present disclosure, the artificial intelligence model for outputting a score corresponding to a patch image may input feature information of each patch image, and the artificial intelligence model for outputting red blood cell information may input feature information of a plurality of patch images. The feature information may include a plurality of types of feature information described with reference to FIG. 5.

[0121] In one embodiment of the present disclosure, the device (2000) may select a target patch image (730) based on the score of the patch image. In one embodiment of the present disclosure, the device (2000) may select a patch image with the highest score among a plurality of patch images as the target patch image (730). Referring to FIG. 7, a horizontal bar displayed on the right side of each patch image may indicate a score for each patch image. For example, the device (2000) may determine a target patch image (730) with the highest score among a plurality of patch images.

[0122] In one embodiment of the present disclosure, the device (2000) can select a target patch image (730) based on an average score of surrounding patch images of the patch image. The device (2000) can determine an average score corresponding to each patch image based on a score corresponding to each patch image and one or more scores corresponding to one or more patch images captured consecutively with each patch image. For example, the device (2000) can determine an average score for scores of 2n+1 patch images including a first patch image, n patch images (where n is a natural number) adjacent to the upper side of the first patch image, and n patch images adjacent to the lower side of the first patch image.

[0123] In one embodiment of the present disclosure, the device (2000) may select a patch image having the highest average score among a plurality of patch images as a target patch image (730). The target patch image (730) having the highest average score among the plurality of patch images may be selected. Referring to FIG. 7, a horizontal bar displayed on the left side of each patch image may indicate an average score for each patch image. The device (2000) may determine a target patch image (730) having the highest average score among the plurality of patch images. In one embodiment of the present disclosure, the average score may include an arithmetic mean in which all scores have equal weights, a weighted mean in which each score has different weights, or a moving average in which the weights change according to the distance from the patch image.

[0124] In one embodiment of the present disclosure, the device (2000) may acquire a region of interest (740) based on a target patch image (730). For example, the device (2000) may determine the region of interest (740) to include the target patch image (730). The region of interest (740) may be determined to have a boundary that is spaced apart by a predetermined distance from a position of the target patch image (730). For example, the device (2000) may determine an upper boundary of the region of interest (740) that is spaced apart by a first distance from a position of the target patch image (730), and may determine a lower boundary of the region of interest (740) that is spaced apart by a second distance from the position of the target patch image (730). For example, referring to FIG. 7, the region of interest (740) may be determined to include an upper boundary and a lower boundary that are spaced apart by a predetermined distance from a position of the target patch image (730). For example, the region of interest (740) may further include four patch images above and five patch images below the target patch image (730). In the present disclosure, the upper and lower sides may be determined along the long axis direction of the blood smear slide.

[0125] In one embodiment of the present disclosure, the device (2000) can determine a staining region (750) for a blood smear slide based on a region of interest (740). The staining region (750) may refer to a region on the blood smear slide where the device performs staining. In one embodiment of the present disclosure, the device (2000) can determine the staining region (750) to include the region of interest (740). Although FIG. 7 describes that the region of interest and the staining region have different sizes in one embodiment of the present disclosure, this is not limited thereto, and the staining region may be determined to be the same as the region of interest. For example, the device (2000) can perform staining on the region of interest (740).

[0126] FIG. 8 is a drawing for explaining a blood smear slide on which staining has been performed, in one embodiment of the present disclosure.

[0127] Referring to FIG. 8, a blood smear slide (100) is illustrated in which staining has been performed on a staining region (820). In one embodiment of the present disclosure, the device (2000) can perform staining on the blood smear slide based on a region of interest. For example, the device (2000) can perform staining on the region of interest or on a staining region that includes the region of interest. In one embodiment of the present disclosure, the device (2000) can perform fixation on the blood smear slide prior to the staining operation. For example, the device (2000) can perform a fixation process on blood as described in step S240 of FIG. 2.

[0128] In one embodiment of the present disclosure, a dyeing region (820) may be determined by the device (2000) to include a target patch image (810). The upper and lower boundaries of the dyeing region (820) may be determined based on a position of the target patch image (810). For example, the upper and lower boundaries of the dyeing region (820) may be determined to be spaced apart by a predetermined distance from the center of the target patch image.

[0129] In one embodiment of the present disclosure, the left and right boundaries of the staining area (820) can be determined based on the target patch image (810) or the blood smear slide (100).

[0130] In one embodiment of the present disclosure, the left border and the right border of the staining region (820) may be determined based on the blood smear slide (100). For example, the left border and the right border of the staining region (820) may be determined to be a predetermined distance away from the left border and the right border of the blood smear slide (100). For example, the left border of the staining region (820) may be determined to be a predetermined distance away from the left border of the blood smear slide (100), and the right border of the staining region (820) may be determined to be a predetermined distance away from the right border of the blood smear slide (100), regardless of the target patch image (810).

[0131] In one embodiment of the present disclosure, the left and right boundaries of the dyed area (820) may be determined based on the location of the target patch image (810). For example, the left and right boundaries of the dyed area (820) may be determined to be spaced apart by a predetermined distance from the center of the target patch image.

[0132] In one embodiment of the present disclosure, the device (2000) determines a target patch image from among a plurality of patch images, and determines a region of interest using the target patch image, thereby performing staining in an area suitable for cell observation. The method of determining a region of interest of the device (2000) allows the user to obtain an objective and highly accurate cell observation area. Furthermore, since staining can be performed and analyzed on a portion of a blood smear slide rather than the entirety of the slide, efficient cell observation is possible by reducing process time and controlling unnecessary operations.

[0133] FIG. 9 is a flowchart of a method for determining an analysis area of ​​a blood smear slide on which staining has been performed, in one embodiment of the present disclosure.

[0134] In one embodiment of the present disclosure, a method for determining an analysis area of ​​a stained blood smear slide may be performed by a device (2000). For example, the device (2000) may perform each step of the method for determining an analysis area of ​​a stained blood smear slide by having a processor of the device (2000) execute at least one instruction contained in a memory. The processor controlling the device (2000) may perform image processing and operations performed by artificial intelligence. In one embodiment, the processor may include an artificial intelligence processor. In one embodiment, the processor may include a plurality of processors.

[0135] In step S910, the device (2000) may acquire a plurality of second patch images of the stained slide. For example, the device (2000) may acquire a plurality of second patch images by photographing a stained area of ​​the stained slide. In one embodiment of the present disclosure, the stained area may include a region of interest. For example, the stained area may be determined to be identical to the region of interest or may be determined to include the region of interest. In the present disclosure, the second patch image may refer to an image of a stained area of ​​a blood smear slide. The second patch image may correspond to a portion of the stained area. For example, the second patch image may capture stained cells.

[0136] In one embodiment of the present disclosure, the device (2000) can obtain a second patch image by photographing a portion of a stained area. The device (2000) can obtain a second patch image by dividing and photographing a stained area of ​​a blood smear slide. For example, the device (2000) can obtain a plurality of second patch images by dividing the stained area into N equal parts in the vertical direction and M equal parts in the horizontal direction and photographing the divided stained areas. In one embodiment of the present disclosure, the device (2000) can perform multiple photographing of the same area by changing the focal length differently.

[0137] In step S920, the device (2000) can obtain a plurality of second scores corresponding to each of the plurality of second patch images.

[0138] In one embodiment of the present disclosure, the device (2000) can obtain second cell information corresponding to the second patch image. The device (2000) can identify the location, size, and / or shape of the cells included in the patch image. The device (2000) can obtain the second cell information using an artificial intelligence model. In one embodiment of the present disclosure, the device (2000) can perform a process of changing the color before inputting the second patch image to the artificial intelligence model. For example, the device (2000) can perform a process of converting the second patch image to a black and white image before inputting it to the artificial intelligence model. If the image input to the artificial intelligence model is black and white, the device (2000) can obtain the second cell information included in the patch image using the same artificial intelligence model before and after staining.

[0139] In one embodiment of the present disclosure, the device (2000) can obtain second feature information corresponding to the second patch image based on the second cell information. The device (2000) can determine information regarding relationships between cells included in the second patch image and / or information regarding the number or area of ​​cells included in the patch image.

[0140] In one embodiment of the present disclosure, the device (2000) may obtain a second score corresponding to the second patch image based on the second feature information. The second score may be a value related to whether the patch image corresponds to the analysis area. For example, the device (2000) may obtain a relatively high second score for a second patch image determined to correspond to the analysis area. The device (2000) may obtain a relatively low score for a second patch image determined not to correspond to the analysis area. For example, the score may be a confidence value related to whether the second patch image corresponds to the analysis area. In one embodiment of the present disclosure, the analysis area may mean an area suitable for analyzing stained blood.

[0141] In step S930, the device (2000) may select a second target patch image for analyzing the stained cells based on a plurality of second scores. In one embodiment of the present disclosure, the device (2000) may select a second patch image having a second score greater than a threshold value as the second target patch image. For example, the device (2000) may select a second patch image having a second score greater than a predetermined value as the second target patch image.

[0142] In step S940, the device (2000) may determine an analysis area based on the second target patch image. In one embodiment of the present disclosure, the device (2000) may select from among a plurality of second patch images such that the plurality of second target patch images are sequentially captured. For example, only the second patch images that are sequentially captured among the second patch images having a second score greater than a threshold value along the long axis of the slide may be determined as the second target patch images.

[0143] FIG. 10 is a block diagram illustrating a device for obtaining red blood cell information using an image of a blood smear slide according to one embodiment of the present disclosure.

[0144] As illustrated in FIG. 10, a device (2000) according to one embodiment of the present disclosure may include a processor (2100), an image capture unit (2200), and a memory (2300). Not all components of the device (2000) are essential, and each component may be added or subtracted.

[0145] According to one embodiment of the present disclosure, the processor (2100) can control the overall operation of the device (2000). The processor (2100) can control the image capture unit (2200) and the memory (2300) by executing programs stored in the memory (2300).

[0146] According to one embodiment of the present disclosure, the processor (2100) may include an artificial intelligence (AI) processor. The AI ​​processor may be manufactured in the form of a dedicated hardware chip for artificial intelligence (AI), or may be manufactured as part of an existing general-purpose processor (e.g., CPU or application processor) or a graphics-only processor (e.g., GPU - Graphic Processing Unit) and mounted on the device (2000).

[0147] According to one embodiment of the present disclosure, the processor (2100) may perform a control operation according to a program for obtaining red blood cell information using an image of a blood smear slide in the device (2000). The processor (2100) may perform the method for obtaining red blood cell information described through FIGS. 1 to 9 of the present disclosure.

[0148] Patch images for blood smear slides according to one embodiment of the present disclosure and / or parameters of an artificial intelligence model may be stored in memory (2300).

[0149] According to one embodiment of the present disclosure, the image capture unit (2200) can capture patch images for a blood smear slide. The image capture unit (2200) can include a precision camera. The camera of the image capture unit (2200) may be configured as a CMOS sensor, but is not limited thereto. The image capture unit (2200) can be configured with sensors for performing an imaging technique (e.g., X-ray, MRI, CT, or PET). An image including a specimen (e.g., a cell, bacteria, fungus, mite, parasite, virus, etc.) captured by the image capture unit (2200) can be subjected to image processing and / or graphic processing by the processor (2100) for image classification. The device (2000) can capture patch images for specimens by the processor (2100) executing one or more instructions stored in the memory (2300). The device (2000) can capture images using the image capture unit (2200).

[0150] According to one embodiment of the present disclosure, by the processor (2100) executing one or more instructions stored in the memory (2300), the device (2000) can obtain multiple patch images for a blood smear slide. By the processor (2100) executing one or more instructions stored in the memory (2300), the device (2000) can obtain cell information about one or more cells included in each of the multiple patch images. By the processor (2100) executing one or more instructions stored in the memory (2300), the device (2000) can obtain feature information for each of the multiple patch images based on the cell information. By the processor (2100) executing one or more instructions stored in the memory (2300), the device (2000) can obtain multiple patch images for a blood smear slide. By the processor (2100) executing one or more instructions stored in the memory (2300), the device (2000) can obtain cell information about one or more cells included in each of the plurality of patch images. By the processor (2100) executing one or more instructions stored in the memory (2300), the device (2000) can obtain feature information about the plurality of patch images based on the cell information. By the processor (2100) executing one or more instructions stored in the memory (2300), the device (2000) can obtain red blood cell information about a blood smear slide based on the feature information. By the processor (2100) executing one or more instructions stored in the memory (2300), the device (2000) can provide red blood cell information. By the processor (2100) executing one or more instructions stored in the memory (2300), the device (2000) can perform staining on the blood smear slide. By causing the processor (2100) to execute one or more instructions stored in the memory (2300), the device (2000) can perform analysis using a blood smear slide on which staining has been performed.

[0151] FIG. 11 is a block diagram illustrating a device for obtaining red blood cell information using an image of a blood smear slide according to one embodiment of the present disclosure.

[0152] As illustrated in FIG. 11, a device (2000) according to one embodiment of the present disclosure may include, in addition to the components of FIG. 10, a cartridge loader unit (2400), an image inspection unit (2500), a user output interface (2600), and a user input interface (2700). Not all components of the device (2000) are essential, and each component may be added or subtracted depending on the design concept of the manufacturer.

[0153] In one embodiment of the present disclosure, the processor (2100) can control the overall operation of the device (2000). The processor (2100) can control at least one of the cartridge loader unit (2400), the image inspection unit (2500), the image capture unit (2200), the user output interface (2600), the user input interface (2700), and the memory (2300) by executing programs stored in the memory (2300).

[0154] The cartridge loader unit (2400) is a unit that obtains a cartridge containing a specimen, and after the cartridge is loaded, the specimen can be smeared and mounted so that it can be inspected by the image inspection unit (2500).

[0155] The image inspection unit (2500) is an optical device, such as a microscope, that can magnify and view a specimen area. The image inspection unit (2500) may be provided together with the device (2000) or may be a separately provided optional device. The image inspection unit (2500) can be used to magnify and confirm a smeared specimen placed on the cartridge loader unit (2400).

[0156] The image capture unit (2200) can capture images of red blood cell specimens identified through the image inspection unit (2500). In one embodiment, the device (2000) can capture images of the entire area of ​​a slide contained in a cartridge. In one embodiment, the device (2000) can sequentially capture images of partial areas of a slide contained in a cartridge.

[0157] The user output interface (2600) is for outputting audio signals or video signals and may include a display unit (2610). Although not shown, the user output interface (2600) may optionally include an audio output unit at the manufacturer's option.

[0158] According to one embodiment of the present disclosure, the device (2000) can display information related to the device (2000) through the display unit (2610). For example, the medical level determined by the device (2000) and information related to the medical level can be displayed on the display unit (2610).

[0159] According to one embodiment of the present disclosure, the display unit (2610) and the touchpad may be configured as a touch screen by forming a layer structure. When the display unit (2610) and the touchpad are configured as a touch screen by forming a layer structure, the display unit (2610) may be used as an input device in addition to an output device. The display unit (2610) may include at least one of a liquid crystal display, a thin film transistor-liquid crystal display, a light-emitting diode (LED), an organic light-emitting diode (OLED), a flexible display, a 3D display, and an electrophoretic display. In addition, depending on the implementation form of the device (2000), two or more display units (2610) may be included.

[0160] According to one embodiment of the present disclosure, the user output interface (2600) can output medical levels and information related to the medical levels through the display unit (2610). According to one embodiment of the present disclosure, the output interface (2500) can also display the current power level, operation mode (e.g., image inspection mode, image classification mode, sleep mode, etc.), etc.

[0161] The user input interface (2700) is for receiving input from a user. The user input interface (2700) may be at least one of a key pad, a dome switch, a touch pad (contact electrostatic capacitance type, pressure resistive film type, infrared detection type, surface ultrasonic conduction type, integral tension measurement type, piezo effect type, etc.), a jog wheel, and a jog switch, but is not limited thereto.

[0162] The user input interface (2700) may include a voice recognition module. For example, the device (2000) may receive a voice signal, which is an analog signal, through a microphone, and convert the voice portion into computer-readable text using an Automatic Speech Recognition (ASR) model. The device (2000) may interpret the converted text using a Natural Language Understanding (NLU) model to obtain the user's utterance intent. Here, the ASR model or the NLU model may be an artificial intelligence model. The artificial intelligence model may be processed by an artificial intelligence processor designed with a hardware structure specialized for processing artificial intelligence models. In this case, the processor (2100) may be an artificial intelligence processor. The artificial intelligence model may be created through training. Here, being created through training means that a basic artificial intelligence model is trained using a plurality of training data by a training algorithm, thereby creating a predefined operation rule or artificial intelligence model set to perform a desired characteristic (or purpose). The artificial intelligence model may be composed of multiple neural network layers. Each of the multiple neural network layers has multiple weight values, and performs neural network operations through operations between the operation results of the previous layer and the multiple weight values.

[0163] Linguistic understanding is the technology of recognizing, applying, and processing human language / characters, including natural language processing, machine translation, dialog systems, question answering, and speech recognition / synthesis.

[0164] The memory (2300) may store a program for processing and controlling the processor (2100), and may store input / output data (e.g., diagnostic information of the device (2000), an image of a sample area, or information related to a medical level). The memory (2300) may also store an artificial intelligence model.

[0165] The memory (2300) may include at least one type of storage medium among a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (e.g., SD or XD memory, etc.), a RAM (Random Access Memory), a SRAM (Static Random Access Memory), a ROM (Read-Only Memory), an EEPROM (Electrically Erasable Programmable Read-Only Memory), a PROM (Programmable Read-Only Memory), a magnetic memory, a magnetic disk, and an optical disk. In addition, the control device (2000) may operate a web storage or cloud server that performs a storage function on the Internet.

[0166] The communication unit (2800) may include a short-range communication unit (2810) and a long-range communication unit (2820). The short-range communication unit (2810, short-range wireless communication interface) may include, but is not limited to, a Bluetooth communication unit, a BLE (Bluetooth Low Energy) communication unit, a near field communication interface, a WLAN (Wi-Fi) communication unit, a Zigbee communication unit, an IrDA (infrared Data Association) communication unit, a WFD (Wi-Fi Direct) communication unit, a UWB (Ultra Wideband) communication unit, an ANT+ communication unit, etc. The long-range communication unit (2820) transmits and receives a wireless signal with at least one of a base station, an external terminal, and a server on a mobile communication network. Here, the wireless signal may include various types of data according to a voice call signal, a video call call signal, or a text / multimedia message transmission and reception. The remote communication unit (2820) may include, but is not limited to, a 3G module, a 4G module, a 5G module, an LTE module, an NB-IoT module, an LTE-M module, etc.

[0167] According to one embodiment of the present disclosure, communication can be performed with a server or other electrical device external to the device (2000) through the communication unit (2800) and data can be transmitted and received. The communication unit (2800) may be optionally included for the purpose of sales or price competitiveness of the device (2000), or may not be included if communication is not required.

[0168] A method according to an embodiment of the present disclosure may be implemented in the form of program commands that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program commands, data files, data structures, etc., alone or in combination. The program commands recorded on the medium may be those specially designed and configured for the present disclosure or may be known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and hardware devices specially configured to store and execute program commands, such as ROMs, RAMs, and flash memories. Examples of program commands include not only machine language codes generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter, etc.

[0169] An embodiment of the present disclosure may also be implemented in the form of a recording medium containing computer-executable instructions, such as program modules, executed by a computer. Computer-readable media may be any available media that can be accessed by a computer, and includes both volatile and nonvolatile media, removable and non-removable media. Furthermore, computer-readable media may include both computer storage media and communication media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information, such as computer-readable instructions, data structures, program modules, or other data. Communication media typically contains computer-readable instructions, data structures, program modules, or other data in a modulated data signal, such as a carrier wave, or other transport mechanism, and includes any information delivery media. Furthermore, some embodiments of the present disclosure may also be implemented as a computer program or computer program product containing computer-executable instructions, such as a computer program that is executed by a computer.

[0170] A device-readable storage medium may be provided in the form of a non-transitory storage medium. Here, the term "non-transitory storage medium" simply means a tangible device that does not contain signals (e.g., electromagnetic waves). This term does not distinguish between cases where data is permanently stored in the storage medium and cases where data is temporarily stored. For example, a "non-transitory storage medium" may include a buffer in which data is temporarily stored.

[0171] According to one embodiment, the method according to one embodiment of the present disclosure may be installed in a memory within a device and executed by a processor of the device. According to one embodiment, the method according to one embodiment of the present disclosure may be provided as included in a computer program product. The computer program product may be traded as a commodity between a seller and a buyer. The computer program product may be distributed in the form of a machine-readable storage medium (e.g., compact disc read only memory (CD-ROM)), or may be distributed online (e.g., downloaded or uploaded) through an application store or directly between two user devices (e.g., smartphones). In the case of online distribution, at least a portion of the computer program product (e.g., a downloadable app) may be at least temporarily stored or temporarily generated in a machine-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or a relay server.

Claims

1. A method for obtaining red blood cell information using an image of a blood smear slide, A step of acquiring multiple patch images for a blood smear slide; A step of obtaining cell information about one or more cells included in each of the plurality of patch images; A step of obtaining feature information for the plurality of patch images based on the cell information; A step of obtaining red blood cell information for a blood smear slide based on the above characteristic information; A step of providing the above red blood cell information; A step of performing staining on the above blood smear slide; and A method comprising the step of performing an analysis using a blood smear slide on which the above staining has been performed.

2. In paragraph 1, The step of obtaining the above multiple patch images is: A step of identifying a plurality of photographing areas for the blood smear slide; and A method comprising the step of obtaining the plurality of patch images each corresponding to the plurality of shooting areas by photographing the plurality of shooting areas.

3. In paragraph 2, A method, characterized in that the plurality of photographing areas are a portion of the blood smear slide determined along the longitudinal direction of the blood smear slide.

4. In paragraph 1, The step of obtaining cell information about one or more cells included in each of the plurality of patch images comprises: A step of inputting each of the plurality of patch images into a classification model to obtain cell information for each of the patch images, A method characterized in that the cell information includes information about at least one of the position, size, or shape of each cell included in each patch image.

5. In paragraph 1, The feature information for the plurality of patch images includes at least one of first feature information, second feature information, third feature information, fourth feature information, fifth feature information, and sixth feature information for each patch image, The above first feature information includes information about the number of cells included in each patch image, The second feature information includes information about the Voronoi area associated with the cells included in each of the patch images, The third feature information includes information about the distance between cells included in each patch image, The fourth feature information includes information about the distance from a plurality of predetermined points in each of the patch images to the nearest cell, The fifth feature information includes information related to the size of the cells included in each patch image, A method wherein the sixth feature information includes information about the area ratio of cells included in each patch image.

6. In paragraph 1, The feature information for the plurality of patch images includes at least one of the seventh feature information, the eighth feature information, and the ninth feature information for each patch image, The above seventh feature information includes information related to the values ​​of color components included in each of the above patch images, The above eighth feature information includes information related to the shooting area for each of the patch images, A method wherein the above ninth feature information includes information related to the number of red blood cells included in each of the patch images.

7. In paragraph 1, The above red blood cell information includes at least one of a hemoglobin level and a hematocrit level for blood included in the blood smear slide, The step of providing the above red blood cell information is: A method comprising the step of outputting the hemoglobin level, evaluation information for the hemoglobin level, the hematocrit level, and evaluation information for the hematocrit level through a display.

8. In paragraph 1, The step of obtaining red blood cell information for a blood smear slide based on the above characteristic information is: A step of obtaining the red blood cell information by inputting the above characteristic information into an artificial intelligence model, A method characterized in that the artificial intelligence model is trained using feature information determined based on a training image in which unstained cells are photographed and red blood cell information corresponding to the training image.

9. In paragraph 1, The step of performing staining on the above blood smear slide is: Comprising a step of performing staining for CBC test, The step of performing analysis using the blood smear slide on which the above staining was performed is as follows: A method comprising the step of determining at least one of the number of blood cells contained in the blood and the white blood cell differential count.

10. In paragraph 1, The step of performing staining on the above blood smear slide is: A step of determining a dyeing area based on the plurality of patch images; A step of performing fixation on the above blood smear slide; A method comprising the step of performing staining on a staining area of ​​the blood smear slide.

11. In a device for classifying cells included in an image, memory containing one or more instructions; and Contains at least one processor, The at least one processor executes the one or more instructions, thereby causing the device to Acquire multiple patch images for blood smear slides, Obtain cell information about one or more cells included in each of the plurality of patch images, Obtaining feature information for the plurality of patch images based on the above cell information, Obtain red blood cell information for a blood smear slide based on the above characteristic information, Provide the above red blood cell information, Staining is performed on the above blood smear slide, A device for performing analysis using a blood smear slide on which the above staining has been performed.

12. In paragraph 11, The at least one processor executes the one or more instructions, thereby causing the device to Identify multiple photographic areas on the above blood smear slide, A device that acquires a plurality of patch images corresponding to each of the plurality of shooting areas by photographing the plurality of shooting areas.

13. In paragraph 12, A device characterized in that the plurality of photographing areas are a portion of the blood smear slide determined along the longitudinal direction of the blood smear slide.

14. In paragraph 11, The at least one processor executes the one or more instructions, thereby causing the device to By inputting each of the above plurality of patch images into a classification model, cell information for each of the above patch images is obtained, A device characterized in that the cell information includes information about at least one of the position, size, or shape of each cell included in each patch image.

15. In paragraph 11, The feature information for the plurality of patch images includes at least one of first feature information, second feature information, third feature information, fourth feature information, fifth feature information, and sixth feature information for each patch image, The above first feature information includes information about the number of cells included in each patch image, The second feature information includes information about the Voronoi area associated with the cells included in each of the patch images, The third feature information includes information about the distance between cells included in each patch image, The fourth feature information includes information about the distance from a plurality of predetermined points in each of the patch images to the nearest cell, The fifth feature information includes information related to the size of the cells included in each patch image, A device wherein the sixth feature information includes information about the area ratio of cells included in each patch image.

16. In paragraph 11, The feature information for the plurality of patch images includes at least one of the seventh feature information, the eighth feature information, and the ninth feature information for each patch image, The above seventh feature information includes information related to the values ​​of color components included in each of the above patch images, The above eighth feature information includes information related to the shooting area for each of the patch images, A device wherein the ninth characteristic information includes information related to the number of red blood cells included in each patch image.

17. In paragraph 11, The above red blood cell information includes at least one of a hemoglobin level and a hematocrit level for blood included in the blood smear slide, The at least one processor executes the one or more instructions, thereby causing the device to A device that outputs the hemoglobin level, evaluation information for the hemoglobin level, the hematocrit level, and evaluation information for the hematocrit level through a display.

18. In paragraph 11, The at least one processor executes the one or more instructions, thereby causing the device to By inputting the above characteristic information into an artificial intelligence model, the above red blood cell information is obtained, A device characterized in that the artificial intelligence model is trained using feature information determined based on a training image in which unstained cells are photographed and red blood cell information corresponding to the training image.

19. In paragraph 11, The at least one processor executes the one or more instructions, thereby causing the device to Perform staining for CBC test, A device for determining at least one of the number of blood cells contained in the blood and the differential count of white blood cells.

20. A computer-readable recording medium having recorded thereon a program for performing the method of any one of claims 1 to 10 on a computer.

Images