CN111684279B

CN111684279B - Cell analysis method, cell analysis device and storage medium

Info

Publication number: CN111684279B
Application number: CN201880088546.3A
Authority: CN
Inventors: 祁欢; 叶燚; 李朝阳
Original assignee: Shenzhen Mindray Bio Medical Electronics Co Ltd; Shenzhen Mindray Scientific Co Ltd
Current assignee: Shenzhen Mindray Bio Medical Electronics Co Ltd; Shenzhen Mindray Scientific Co Ltd
Priority date: 2018-08-02
Filing date: 2018-08-02
Publication date: 2023-02-21
Anticipated expiration: 2038-08-02
Also published as: CN111684279A; WO2020024227A1

Abstract

A cell analysis method, a cell analysis apparatus (100), and a storage medium include: obtaining a digital image (201) of cells in a blood sample; outputting a digital image (202) of cells in the blood sample; receiving voice information; the digital images of the cells in the blood sample are processed or manipulated accordingly based on the received speech information (204).

Description

Cell analysis method, cell analysis device and storage medium

Technical Field

The present invention relates to medical device technologies, and in particular, to a cell analysis method, a cell analysis apparatus, and a storage medium.

Background

In the process of classifying cell samples in relative smears, although a machine can be used for finishing classification work, the cell samples which are difficult or complicated to image need to be manually checked and classified, in the related technology, when the cell classification work is manually finished, cell images need to be manually dragged to enter corresponding classification areas, but when a large number of cell samples which need to be checked and classified are faced, the cell images are manually dragged in a mode that the operation speed is low, meanwhile, dragging errors are easy to occur in the dragging process, and the accuracy and precision of cell classification are influenced.

Disclosure of Invention

Embodiments of the present invention provide a cell analysis method, a cell analysis apparatus, and a storage medium, which can efficiently and accurately classify cells.

The technical scheme of the embodiment of the invention is realized as follows:

the embodiment of the invention provides a method applied to cell analysis, which comprises the following steps:

obtaining a digital image of cells in a blood sample;

outputting a digital image of cells in the blood sample;

selecting at least one cell in the digital image of cells in the blood sample, the selected at least one cell being in a selected state;

receiving voice information;

recognizing the voice information, and determining the type of the cell in the selected state according to the voice information when the voice information is determined to be used for verifying the type of the cell in the selected state;

outputting or storing the determined species of the cells in the selected state.

An embodiment of the present invention further provides a cell analysis apparatus, including:

an image receiving device configured to obtain a digital image of cells in a blood sample;

a display output device configured to output a digital image of the blood sample;

a processing device configured to select at least one cell in the digital image of cells in the blood sample, the selected at least one cell being in a selected state;

a voice recognition device configured to receive and recognize voice information;

the voice recognition device is configured to determine the type of the cell in the selected state according to the voice information when the voice information is determined to be used for determining the type of the cell in the selected state;

the voice recognition device is configured to output the approved species of the cells in the selected state;

a storage device configured to store the nucleated species of the cell in the selected state.

a memory for storing executable instructions;

and the processor is used for executing the executable instructions stored in the memory to execute the cell analysis method provided by the embodiment of the invention.

The embodiment of the invention also provides a storage medium, which stores an executable program and is used for realizing the cell analysis method provided by the embodiment of the invention when a processor executes the executable program.

In the embodiment of the invention, the digital image of the cells in the received blood sample is output to correspond to the selected state of at least one cell in the blood sample, and then the types of the cells in the selected state are verified by identifying the voice information, so that the manual re-inspection and classification work in the process is saved, the problems of classification errors and low efficiency caused by manual operation are avoided, and the manual cell classification process is simplified.

Drawings

FIG. 1 is a schematic view of an alternative configuration of a cell analysis apparatus according to an embodiment of the present invention;

FIG. 2 is a schematic flow chart of an alternative method of cell analysis provided in an embodiment of the present invention;

FIG. 3 is a schematic view of an alternative structure of a cell analysis apparatus according to an embodiment of the present invention;

FIG. 4A is a schematic diagram of an image display in a cell analysis method provided in an embodiment of the present invention;

FIG. 4B is a schematic diagram of a cell counting operation performed by the cell analysis apparatus according to the embodiment of the present invention;

FIG. 4C is a schematic diagram of a cell counting operation performed by the cell analysis apparatus according to the embodiment of the present invention;

FIG. 5 is a schematic view of an alternative structure of the cell analysis device according to the embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to the accompanying drawings. The present invention should not be construed as limited to the embodiments set forth herein, but rather the embodiments set forth herein are presented to enable those skilled in the art to make and use the invention in a full and complete manner and to convey the concept of the embodiments to others skilled in the art and, therefore, other embodiments obtained by those skilled in the art without the exercise of inventive faculty are within the scope of the invention.

Before further detailed description of the present invention, terms and expressions referred to in the embodiments of the present invention are described, and the terms and expressions referred to in the embodiments of the present invention are applicable to the following explanations.

1) Blood cell analysis, namely a blood cell analyzer measures cells such as red blood cells and white blood cells in blood by cell signals, including classification and counting, for example, including items such as red blood cells, hemoglobin, white blood cell count and classification thereof, platelet count and the like; by way of example, the types of cell signals may include photoelectric, capacitive, resistive, centrifugal, and laser scattering types, among others.

2) Blood cell classification, which is the classification of cells in blood, can be three classifications for leukocytes, including small cell populations (lymphocytes), intermediate cell populations (eosinophils, basophils, and monocytes), and large cell populations; for another example, leukocytes can be classified into five categories, including: neutrophils/neutrophiles/eosinophils/basophils, lymphocytes and monocytes.

3) The push sheet is used for forming a blood cell thin layer on the slide by a push sheet machine or manually so as to be convenient for observing through a microscope, for example, when the push sheet machine is used for preparing a smear by using a blood sample, a liquid drop of blood is dripped on one slide, the other slide is taken as a push sheet, the push sheet is moved from one side of the liquid drop to the other side, and the blood cell thin layer is formed on the slide, so that the blood cell thin layer can be analyzed by a blood cell analyzer; in addition, the mode of making blood smear can be that two slides are "pushed" to bleed the thin layer of blood cells, can also be that it sprays into the thin layer of blood cells.

4) Dyeing, namely dyeing the cells in the smear by using a dyeing machine or manually using a chemical agent so that different types of cells have good identification, and the dyeing machine and the slide pusher can be integrated into a slide dyeing machine.

5) The reader, a cell analysis device (also called a reader), classifies and counts the cells in the blood sample.

6) In response to the condition or state indicating that the executed operation depends on, one or more of the executed operations may be in real-time or may have a set delay when the dependent condition or state is satisfied; there is no restriction on the order of execution of the operations performed unless otherwise specified.

7) Review for manual inspection of images of cells that have undergone type approval or images of more complex cells.

8) The target classification, which defines the type of cells to be detected according to the existing data, for example, the cells to be detected are blood cells, and the target classification information may include: neutrophilic rod shaped nuclear granulocyte, neutrophilic lobular nuclear granulocyte, eosinophilic granulocyte, basophilic granulocyte and lymphocyte, etc.

9) And (4) pre-classifying, namely automatically classifying the cells to be detected by the cell analysis device, and classifying the cells into target classification information.

10 Type) is assigned, the type of cells that have been pre-classified or not is assigned.

Fig. 1 is a schematic diagram of an alternative structure of a cell analysis apparatus 100 according to an embodiment of the present invention, and the modules in fig. 1 are described below.

An image receiving device 101 configured to obtain a digital image of cells in the blood sample.

In one embodiment of the present invention, the cell analysis apparatus further comprises an imaging device, the image receiving device 101 can be further connected to an imaging device (not shown in the figure), the imaging device is configured to perform photoelectric conversion on the light transmitted through the blood sample and passing through the lens set to form a digital image of the cells in the blood sample; the imaging device may be a part of the cell analysis device 100 or an external device to the cell analysis device 100.

In one embodiment of the invention, the imaging device may be configured to take a picture of the cells in the blood sample to form a digital image of the cells in the blood sample.

A display output device 102 configured to output a digital image of the blood sample.

A processing device 103 configured to perform corresponding processing or operation on the digital images of the cells in the blood sample according to the received voice information.

In one embodiment of the invention, the processing device 103 is configured to select at least one cell in the digital image of cells in the blood sample, the selected at least one cell being in a selected state;

a display output device 102 configured to output the selected status corresponding to the at least one cell in the blood sample to a screen.

In one embodiment of the present invention, the display output device 102 is further configured to output a digital image of the cells in the blood sample, and a pre-classification of the corresponding cells, into a screen. Through the technical scheme of the embodiment of the invention, the digital image of the cells in the blood sample and the pre-classification corresponding to the digital image can be output to a screen, so that the pre-classification can be detected, and the wrong classification information can be avoided.

In an embodiment of the present invention, the display output device 102 is further configured to output the digital image of the cells in the blood sample and the target classification information of the cells to a screen; the voice recognition device is configured to determine an approval type of a cell in a selected state according to the voice information when determining that the type of the voice information approval is one of the target classifications, and specifically, the voice recognition device can determine whether the type of the voice information approval is one of the target classifications, where the type of the cell approval includes: performing a verification of at least one cell type in the target classification information; the type of the cell being selected is one of the target classes. The method comprises the steps of classifying a target classification, pre-classifying, classifying and classifying, wherein the classification is one of target classifications, and is performed through artificial voice, and the pre-classification is also one of target classifications and is realized through machine classification. Through the technical scheme shown in the embodiment of the invention, the digital image of the cells in the blood sample and the target classification information corresponding to the digital image can be output to the screen, so that whether the corresponding target classification information is appropriate or not can be judged, and the cell target classification information in the blood sample can be timely adjusted.

In an embodiment of the present invention, the display output device 102 is further configured to output the digital image of the cells in the blood sample, the target classification information of the cells and the pre-classification information of the cells into the screen; the voice information is used for characterizing the matching relation between the pre-classification information for verifying the cells and the target classification information of the cells. Through the technical scheme of the embodiment of the invention, when a user finds that the matching relationship between the pre-classification information of the cells and the target classification information of the cells is incorrect, the pre-classification information of the cells can be timely adjusted so as to improve the accuracy of the cell analysis device in classifying the cells to be detected.

In one embodiment of the invention, the processing device 103 is further configured to identify at least one cell in the digital image of cells in the blood sample before selecting the at least one cell in the digital image of cells in the blood sample; the processing device 103 is further configured to pre-classify the at least one cell into the target classification information, thereby obtaining pre-classification information of the at least one cell in the digital image of the cells in the blood sample. Through the technical scheme shown in the embodiment of the invention, the cell analysis device can realize the pre-classification of the cells to be detected according to the target classification information. For example, the target classification information includes neutrophil, eosinophil, basophil, lymphocyte, and the like, and when the processing device 103 recognizes that a certain cell is a neutrophil, the cell is automatically pre-classified (machine-classified) into a neutrophil in the target classification information.

The category to which the cells are pre-classified (machine-automatically classified) may not be in the target classification information, for example, the target classification lists 20 cell categories, but the cell analysis apparatus 100 may pre-classify a part of the identified cells into the cell categories listed in the target classification, may pre-classify the identified cells into categories other than the 20 cell categories listed in the target classification, and specifically may pre-classify (machine-classify) the cells into which categories, depending on the performance of the cell analysis apparatus 100. When the cell is classified through the voice command, the cell class classified through the voice command belongs to the cell class listed in the target classification, if the cell class classified through the voice command does not belong to one of the cell classes listed in the target classification, the voice command is determined not to be in accordance with preset information or command, and the voice command is not responded.

In an embodiment of the present invention, the display output device 102 is further configured to output a classification region corresponding to at least one of the categories included in the pre-classification to the screen, the classification region including an image of cells belonging to the respective category in the blood sample. Through the technical scheme of the embodiment of the invention, the classification area belonging to at least one cell type can be displayed to a user, so that the batch inspection of the cell classification result is realized, and the inspection efficiency is improved.

In one embodiment of the invention, the pre-classification information represents the category to which the cell belongs by using at least one of characters, graphs, classification areas and classification marks. And the target classification information represents the cell attributive type by adopting at least one of characters, graphs, classification areas or classification marks. Through the technical scheme shown in the embodiment of the invention, the attribution type of the cells can be expressed in various optional modes, and the cells can be switched among various expression forms.

As an example, the imaging device is equipped with a convex lens group (e.g. a microscope or other device with image magnification function) whose different magnifications, e.g. 100 times, 200 times, etc., are formed by a combination of different convex lenses; when the smear is placed in the observation position of the convex lens group of the cell analysis device, the digital camera in the cell analysis device senses the light rays which are sequentially projected from the smear and the convex lens group, and forms a digital image of the amplified cell by a photoelectric conversion principle. For example, the digital camera and the lens set move transversely relative to the plane of the smear, and the automatic movement can be realized by a controller of the cell analysis device, and the manual control movement can also be realized by various human-computer interaction modes, so that the digital image of the blood smearing area in the smear is shot. By the technical scheme shown in the embodiment of the invention, the automatic acquisition of the image of the cell to be observed can be realized.

In one embodiment of the present invention, the display output device may be implemented as a display screen for outputting digital images, and the size of the display screen may be flexibly selected according to the use environment of the cell analysis device. Through the technical scheme of the embodiment of the invention, the generated digital image can be displayed to the user.

In one embodiment of the present invention, an image interface is provided in the cell analysis apparatus for outputting a digital image to a slide reading apparatus connected to the cell analysis apparatus through the image interface, and the types of the image interface include, but are not limited to: HDMI interface, DVI interface, VGA interface, RGB interface, USB interface. Through the technical scheme shown in the embodiment of the invention, the digital image can be output to the external film reading device with larger display area, and the external display device can adapt to different systems so as to adapt to various display environments.

For the selected state, the cells in the selected state may be displayed in a manner that is distinguishable from the cells that have not taken the selected state; for example, cells in the selected state have a greater intensity than cells not in the selected state; alternatively, the display size of cells in the selected state is larger than the display size of cells not in the selected state; or, the cell in the selected state has suggestive characters, symbols or graphics, for example, a graphic element surrounding the cell in the selected state is output to a screen to prompt a user that the cell in the graphic element is in a focused state, so that the cell is convenient for a beginner to use. In particular, the graphical elements may have a dynamic effect, thereby having a high degree of recognition.

In the selected state, the position of the cell in the selected state is at a set position in the screen, for example, the center position of the screen. By the technical scheme of the embodiment of the invention, when the cells in the selected state are switched, a new cell image in the selected state does not need to be searched in a screen, so that the reading speed of a user is improved.

In one embodiment of the present invention, the display output device 102 is further configured to output a digital image of all cells in the blood sample to a screen. By the technical scheme of the embodiment of the invention, the digital images of all cells can be displayed on the screen, so that medical staff can count the proportion of the cells with abnormal morphology to all cells.

In one embodiment of the invention, the display output device 102 is further configured to output a magnified digital image of a set category of cells of all categories involved in the pre-classification into the screen. By the technical scheme shown in the embodiment of the invention, the directional display of the cells of the set types can be realized, so that the medical staff can conveniently review the cells of the set types.

In an embodiment of the present invention, the display output device 102 is further configured to output the selected state corresponding to the target cell of the human-computer interaction operation to the screen in response to the human-computer interaction operation. Through the technical scheme of the embodiment of the invention, the medical staff can select at least one target cell and directionally output the selected state of the target cell to the screen so as to realize the retest of the target cell.

By way of example, the manner of human-computer interaction includes, but is not limited to: a user sends a control instruction through clicking operation; or sending a control command to the cell analysis device through voice operation; and the user sends a control instruction to the cell analysis device through the touch gesture.

In one embodiment of the present invention, the selected state is located at the location of the target cell, and may take the form including, but not limited to, a central location of the screen. By the technical scheme of the embodiment of the invention, when the cells in the selected state are switched, the cells do not need to be searched in a screen, so that the film reading speed of a user is improved.

As an example, the selected state corresponding to the one or more cells may be output at a time based on the one or more cells selected by the human-machine interaction operation. Through the technical scheme of the embodiment of the invention, a plurality of cells in a selected state can be output at one time according to the operation of medical personnel, so that the reading efficiency is improved.

In one embodiment of the invention, the interaction operations include, but are not limited to: input and output devices such as a mouse, a keyboard, a trackball and the like. Through the technical scheme shown in the embodiment of the invention, the interactive operation can be controlled in various ways.

In one embodiment of the present invention, the display output device 102 is further configured to output the selected state of switching between cells of the blood sample to the screen in response to a human-machine interaction. Through the technical scheme shown in the embodiment of the invention, the demonstration of the searching process of the cells in the selected state can be realized.

In an embodiment of the present invention, the display output device 102 is further configured to switch the newly acquired cell in the selected state to any cell that has not acquired the selected state, and as an example, images of adjacent cells that have not acquired the selected state may be sequentially output according to the arrangement positional relationship of the cells.

In an embodiment of the present invention, the display output device 102 is further configured to switch the cell in the selected state newly obtained after switching to any cell that has not obtained the selected state, and for example, the display output device may output images of the cell in the selected state that has not obtained at the corresponding position at fixed intervals according to the arrangement position relationship of the cells, or output the cell that meets the display condition in the cell in the selected state that has not obtained.

As an example, the above conditions may include: when all the cells of one class obtain the selected state, the class which does not obtain the selected state is continuously selected, and the selected state switched in the cells of the corresponding class is output. By the technical scheme shown in the embodiment of the invention, the cells to be retested can be sequentially detected, and the omission of detection is avoided.

As another example, the above-mentioned conditions may include: to select based on the arrangement position of cells in the blood sample, cells that are adjacent to cells that released the selected state and have not acquired the selected state are selected. By the technical scheme of the embodiment of the invention, omission of the cell image to be retested can be avoided in the retest process of the cell image.

In one embodiment of the present invention, the display output device 102 is further configured to output the selected state of the at least one cell belonging to the corresponding type in the blood sample to the screen in response to the human-computer interaction indicating the pre-classified category. By the technical scheme of the embodiment of the invention, the image retrieval of the pre-classified cells in the selected state can be realized, so that the cell images can be rechecked.

In one embodiment of the invention, the display output device 102 is further configured to output a selected state of automatic switching between cells of the blood sample to the screen without waiting for a human interaction instruction when the digital image is obtained. Through the technical scheme of the embodiment of the invention, medical staff can conveniently observe the switching between the blood sample cells so as to improve the speed of reinspection.

In one embodiment of the present invention, the display output device 102 is further configured to switch the selected state in the corresponding one or more types of cells when the human-machine interaction operation indicates that the one or more types included in the pre-classification.

Taking the human-computer interaction operation indicating the neutral rod-shaped nuclear granulocytes, the neutral lobular nuclear granulocytes, the eosinophils, the basophils and the lymphocytes in the five cell categories as an example, the cell analysis device can switch the selected state among the cells corresponding to the five cell types and sequentially switch the selected state among the cells in the to-be-selected state corresponding to any one cell type, so as to improve the rechecking speed of the medical staff on the cell images.

By the technical scheme shown in the embodiment of the invention, the directional switching of the images of the selected states of the cells of different types can be realized, so that the corresponding information of the cells of different types can be counted conveniently.

In one embodiment of the invention, the selected state has a set effective time, and in response to the arrival of the effective time of the selected state, the selected state corresponding to unselected cells in the blood sample is output to the screen, so that the cells in the selected state in the screen are switched. Through the technical scheme shown in the embodiment of the invention, the cells to be displayed in a focusing state can be automatically switched, so that the full automation of the reinspection process is realized.

In an embodiment of the present invention, the output device 102 is further configured to output the selected states of the cells to the screen one by one, and the selected state of each cell is switched after the selected state of each cell is kept valid for a period of time, so that the medical staff can re-check the type of the output cells.

A speech recognition device 104 configured to receive and recognize speech information;

the voice recognition device 104 is configured to determine the type of the cell in the selected state according to the voice information when the voice information is determined to be used for determining the type of the cell in the selected state;

the voice recognition device 104 is configured to output the approved species of the cell in the selected state;

in one embodiment of the present invention, the speech recognition device 104 is further configured to determine the pre-classification of the cell in the selected state as the approved classification when the pre-classification of the cell in the selected state is output to the screen and the recognition of the speech operation confirms the pre-classification. Through the technical scheme shown in the embodiment of the invention, the pre-classified type verification of the cells in the selected state through voice operation can be realized.

In one embodiment of the present invention, the speech recognition device 104 is further configured to determine the pre-classification of the cell in the selected state as the approved category when the pre-classification of the cell in the selected state is output to the screen and a particular speech operation is recognized. Through the technical scheme of the embodiment of the invention, the pre-classification of the cells to be re-examined can be realized through voice operation.

By way of example, the specific voice operations include: confirming pre-classified voice operation; or, switching the voice operation of the cell in the selected state, wherein the switching the cell in the selected state includes: the cell in the selected state is switched from the selected state to the unselected state, and the other cell is switched from the unselected state to the selected state. As an example, when a specific voice operation is a voice operation for confirming pre-classification, the re-examination work of the cells is completed, thereby confirming that the classification of the cells to be re-examined is correct; when the specific voice operation is the voice operation for switching the cells in the selected state, the images of the cells to be retested in the selected state can be switched through the voice operation, so that the complicated manual switching operation of medical staff is reduced.

In an embodiment of the present invention, the display output device 102 is further configured to output the classification region where the cell in the selected state is in the corresponding category to the screen when the category of the cell in the selected state, which is determined by the voice operation, is determined. Through the technical scheme of the embodiment of the invention, the cells to be rechecked can be classified through voice operation, so that the manual classification of medical staff is avoided, and the defect that the manual classification is easy to generate errors is avoided.

In an embodiment of the present invention, the voice recognition device 104 is further configured to cancel the type of the cell that has been verified through a voice operation. As an example, when the speech recognition device 104 is configured to cancel the category of the cell that has been verified by the speech operation, the previous classification result may be cleared by the speech operation to achieve a mistake in classifying the existing cell. Through the technical scheme shown in the embodiment of the invention, cells in each classification area can be adjusted according to voice operation, so that the accuracy of cell classification is improved, and the accuracy of cell classification is improved.

In one embodiment of the invention, recognizing the speech information comprises at least one of: performing continuous voice recognition; and initiating a voice recognition operation when the selected state is output. Through the technical scheme of the embodiment of the invention, medical personnel can select the appropriate voice recognition mode according to different use environments so as to adapt to wider use scenes.

In one embodiment of the invention, the pre-classification represents the class to which the cell belongs using at least one of text, graphics, classification region, and classification label.

In one embodiment of the present invention, the speech recognition device 104 is further configured to classify the cellular alteration in the selected state into a category that is defined by the speech information. Wherein the speech recognition device 104 comprises: and when the pre-classification information of the cells in the selected state is output to the screen, and the type approved by the voice information is different from the pre-classification of the cells in the selected state, changing the classification of the cells in the selected state into the type approved by the voice information. At this time, when the type approved by the voice message is different from the pre-classification of the cell in the selected state, it indicates that the previous pre-classification is wrong, and the classification condition of the selected cell can be timely changed by changing and classifying the cell in the selected state to the type approved by the voice message.

In an embodiment of the present invention, the speech recognition device 104 is further configured to keep the pre-classification of the cell in the selected state unchanged when the class identified by the speech information is the same as the pre-classification of the cell in the selected state. The working process of the speech recognition device 104 comprises: and when outputting the pre-classification of the cell in the selected state to the screen and recognizing that the type approved by the voice information is the same as the pre-classification of the cell in the selected state, keeping the pre-classification of the cell in the selected state unchanged. Furthermore, the voice recognition device is further configured to mark the cells in the blood sample of which the type has been verified according to the voice information, so as to realize timely marking of the corresponding cells of the blood sample of which the type has been verified, so that a user can conveniently check which cells are verified, and recheck is not needed. At this time, it is recognized that the type approved by the voice information is the same as the pre-classification of the cell in the selected state, which indicates that the previous pre-classification is correct, the processing efficiency can be improved by keeping the pre-classification of the cell in the selected state unchanged, and the corresponding pre-classification process can be recorded.

In an embodiment of the present invention, the voice recognition device 104 is further configured to classify the cells in the selected state into a category specified by the voice message.

The working process of the speech recognition device 104 comprises the following steps: and when the cell in the selected state is output to the screen and is not pre-classified and the type approved by the voice information is identified, classifying the cell in the selected state into the type approved by the voice information. At this time, since there may be cases such as missing classification in the pre-classification process, when the type specified by the voice information is identified, classifying the cell in the selected state into the type specified by the voice information may classify the cell without pre-classification in time.

In an embodiment of the present invention, the voice recognition device 104 is further configured to recognize that the pre-classification of the cell in the selected state is kept unchanged when the voice information indicates to switch the cell in the selected state. The working process of the speech recognition device 104 comprises: when the pre-classification of the cell in the selected state is output to the screen and the voice information is recognized to indicate that the cell in the selected state is switched, the pre-classification of the cell in the selected state is kept unchanged. At the moment, when the voice information is recognized to indicate that the cells in the selected state are switched, the pre-classification of the cells in the selected state is kept unchanged, the adjacent selected cells are switched through one voice instruction, meanwhile, the pre-classification of the corresponding cells is kept unchanged, and the operation speed of cell classification is improved.

In an embodiment of the present invention, the voice recognition device 104 is further configured to, before recognizing the voice message, turn on a voice recognition function when recognizing that the cell in the selected state exists. When the cell in the selected state is identified, the voice recognition function is started, so that the interference of other voice information of the user on the type approval of the corresponding cell when the cell in the selected state does not exist can be avoided.

In an embodiment of the present invention, the speech recognition device 104 is further configured to turn on a speech recognition function before recognizing the speech information and when recognizing that the artificial cell classification procedure is entered. When the selected cell is identified to enter the artificial cell classification flow, the voice recognition function is started, so that the interference of other voice information on the type verification of the corresponding cell when the selected cell exists but does not enter the artificial cell classification flow can be avoided.

In an embodiment of the present invention, the voice recognition device 104 is further configured to compare the obtained voice information with preset information or instructions; when the voice information corresponds to preset information or instructions, the voice information is responded; and when the voice information does not correspond to the preset information or instruction, the voice information is not responded. For example, when the voice command of the user is classification information, switching information, and information such as confirming classification or canceling classification, which corresponds to pre-stored information or command, the voice recognition device 104 will respond; other voice messages not in accordance with the preset information or command, such as chat messages, noises, etc., are not responded, or the voice command, if not specified, is not in accordance with the preset information or command and is not responded. According to the technical scheme of the embodiment, corresponding voice information may appear for many times in the cell verification process, so that parameters of the corresponding voice information can be set in advance, and when the voice information is received, the acquired voice information is compared with the characteristic parameters of preset verification type voice; and when the corresponding parameters are corresponded, the voice information is responded, so that the accuracy of the cell classification operation is improved.

The storage device 105 is configured to store the kind of the cell under examination.

In an embodiment of the present invention, the application environment is that multiple persons review the same cell image at the same time, and the specific voice operation is from at least two users, and the voice recognition device 104 is configured to recognize the voice operations of at least two users and determine the types of the cells in the selected state that are approved by the voice operations of different users, respectively. The respective storage devices 105 are configured to store the types of cells specified by the users for the same cells, respectively. For example, when a plurality of persons review a selected cell at the same time, different persons have different types of cell identification by voice information, the voice recognition device 104 of the cell analysis device can recognize and record the identification type of the cell by each person, and the display output device 102 can collectively output all the determination results for comparison, for example, for the same image of the cell to be reviewed, the voice recognition device 104 of the cell analysis device can recognize and record the number of times it is determined as neutrophil, or can recognize and record the number of times it is determined as eosinophil.

According to the technical scheme of the embodiment of the invention, in clinical application, in the case of complex detection samples, a plurality of doctors may make a consultation together, and the plurality of doctors may give respective judgment on the samples, so that the cell analysis device can record classification results of a plurality of people on the same cell and record the classification results for retrieval after recheck.

In one embodiment of the present invention, the specific voice operation includes voice operations of at least two persons, and the voice recognition device 104 is configured to recognize the voice operations of at least two persons and respectively determine the category of the cell in the selected state, which is determined by the voice operations.

In one embodiment of the present invention, the voice recognition device 104 is further configured to acquire operation authority values of different users, and the corresponding storage device 105 is configured to store information corresponding to each voice operation, respectively, while marking information corresponding to the highest operation authority value as priority display. According to the technical scheme disclosed by the embodiment of the invention, the cell analysis device can be used under the guidance of a teacher by a practicing doctor, in the process of classifying cells through the cell analysis device, the cell analysis device can endow a lower authority value after identifying the voice operation of the practicing doctor, and endow a higher authority value after identifying the voice operation of the instructing teacher, after (or at the same time) the practicing doctor finishes the classification work, the instructing teacher can check and correct errors in time, and the system corrects according to the judgment made by a user with higher authority value and records and outputs the whole process for teaching reference.

In an embodiment of the present invention, the display output device is further configured to output the statistical information of the classification of the cells in the blood sample after the cell types are determined through the voice information, so as to enable a user to accurately know the classification of the cells in the blood sample.

In one embodiment of the invention, the speech recognition device is configured to determine to count the number of cells in the blood sample based on the speech information when it is determined that the speech information is for counting the number of cells in the blood sample. Further, the determining the count of the number of cells in the blood sample according to the voice information may include: (1) The image of the blood sample is divided into a plurality of counting units with the same area, and each of the divided counting units is numbered. (2) Selecting the statistical cells with corresponding numbers through the processing device 103, and sending cell number information to the voice recognition device 104; furthermore, a certain numbered statistical cell can be selected through a corresponding voice instruction. (3) The voice recognition device 104 recognizes the cell number information represented by the corresponding voice command, and fills the cell number information into the statistical cells with corresponding numbers, so as to complete the statistics of the cell number. Therefore, in the process of counting the number of the cells through the voice command, the user does not need to perform manual operation, the whole counting process is controlled and completed by the voice command, and the operation burden of the user is reduced.

In the above embodiments of the present invention, the image receiving apparatus 101 and the display output apparatus 102 may be implemented by a display, the voice recognition apparatus 104 may be implemented by a controller, and the storage apparatus 105 may be implemented by a memory.

In one embodiment of the present invention, the cell analysis apparatus further comprises:

an imaging device;

the imaging device is configured to capture cells in the blood sample to form a digital image of the cells in the blood sample.

The push piece dyeing machine integrally formed by the dyeing machine and the push piece machine can push smears of dyed blood cells to the imaging device, and the imaging device shoots the cells in the blood sample to form a digital image of the cells in the blood sample.

Fig. 2 is a schematic flow chart of an alternative cell analysis method provided in an embodiment of the present invention, which is applied to a cell analysis apparatus, the cell analysis apparatus including: the device comprises an image receiving device, a display output device, a voice recognition device and a storage device. Referring to fig. 2, an alternative flow chart of the cell analysis method provided in the embodiment of the present invention illustrates the steps shown.

Step 201: a digital image of cells in a blood sample is obtained.

Step 202: a digital image of the cells in the blood sample is output.

The received digital image of the cells in the blood sample may be a digital image of the cells obtained by an external device, or may be formed by shooting by an imaging device carried by the cell analysis device.

In one embodiment of the present invention, the cell analysis device may include an imaging device for forming a digital image of the cells in the blood sample by transmitting the blood sample and performing photoelectric conversion by light through the lens assembly.

In one embodiment of the present invention, outputting a digital image into a screen comprises: a magnified digital image of the cells in the blood sample, and a pre-classification of the corresponding cells, are output to a screen. By the technical scheme of the embodiment of the invention, the amplified digital image of the cells in the blood sample and the pre-classification corresponding to the digital image can be output to a screen, so that the pre-classification can be detected, and wrong classification information can be avoided.

In one embodiment of the invention, outputting into a screen a digital image of cells in a blood sample, and a pre-classification of the corresponding cells, comprises: and outputting a classification area corresponding to at least one category included in the pre-classification to a screen, wherein the classification area comprises an image of cells belonging to the corresponding category in the blood sample. Through the technical scheme of the embodiment of the invention, the classification area belonging to at least one cell type can be displayed to a user, so that the batch inspection of the cell classification result is realized, and the inspection efficiency is improved.

In one embodiment of the present invention, the outputting or storing the digital image of the blood sample comprises: outputting the digital image of the cells in the blood sample and the target classification information of the cells to a screen; the recognizing the voice information, and when determining that the voice information is used for verifying the type of the cell in the selected state, determining the verified type of the cell in the selected state according to the voice information includes:

when the type of the voice information approval is judged to be one of the target classifications, the approval type of the cell in the selected state is determined according to the voice information, wherein the approval type of the cell comprises the following steps: performing a verification of at least one cell type in the target classification information; the nucleated species of the cells in the selected state is one of the target classifications. The method comprises the steps of classifying a target classification, pre-classifying, classifying and classifying, wherein the classification is one of target classifications, and is performed through artificial voice, and the pre-classification is also one of target classifications and is realized through machine classification. By the technical scheme of the embodiment of the invention, the digital image of the cells in the blood sample and the target classification information corresponding to the digital image can be output to the screen, so that whether the corresponding target classification information is appropriate or not can be judged, and the cell target classification information in the blood sample can be timely adjusted.

In one embodiment of the present invention, the outputting the digital image of the blood sample comprises: outputting digital images of cells in the blood sample, target classification information of the cells and pre-classification information of the cells to the screen; the voice information is used for characterizing the matching relation between the pre-classification information for verifying the cells and the target classification information of the cells. Through the technical scheme shown in the embodiment of the invention, when a user finds that the matching relationship between the pre-classification information of the cells and the target classification information of the cells is incorrect, the pre-classification information of the cells can be timely adjusted so as to improve the accuracy of the cell analysis device in classifying the cells to be detected.

In one embodiment of the invention, prior to selecting at least one cell in the digital image of cells in the blood sample, identifying at least one cell in the digital image of cells in the blood sample; pre-classifying the at least one cell to the target classification information, thereby obtaining pre-classification information for the at least one cell in the digital image of cells in the blood sample. Through the technical scheme shown in the embodiment of the invention, the cell analysis device can realize the pre-classification of the cells to be detected according to the target classification information.

In one embodiment of the invention, the pre-classification information represents the category to which the cell belongs by using at least one of characters, graphs, classification areas and classification marks; and the target classification information represents the cell attributive type by adopting at least one of characters, graphs, classification areas or classification marks. Through the technical scheme shown in the embodiment of the invention, the attribution type of the cells can be expressed in various selectable modes, and the two expression forms can be switched.

In one embodiment of the present invention, a convex lens group (e.g., a microscope) is disposed in the cell analysis device, and different magnifications of the lens group are formed by a combination of different convex lenses, such as 100 times, 200 times, etc.; when the smear is placed in the observation position of the convex lens group of the cell analysis device, the digital camera in the cell analysis device senses the light rays which are sequentially projected from the smear and the convex lens group, and forms a digital image of the amplified cell by a photoelectric conversion principle. For example, the digital camera and the lens assembly can be moved laterally relative to the plane of the smear, either automatically by a controller of the cellular analysis device or manually by various human-computer interaction methods, thereby capturing a digital image of the area of the smear of blood in the smear. By the technical scheme shown in the embodiment of the invention, the automatic acquisition of the image of the cell to be observed can be realized.

In one embodiment of the present invention, a display screen is provided in the cell analysis apparatus for outputting a digital image. Through the technical scheme of the embodiment of the invention, the generated digital image can be displayed to the user.

In one embodiment of the present invention, an image interface is provided in the cell analysis apparatus for outputting a digital image to a slide reading apparatus connected to the cell analysis apparatus via the image interface. Through the technical scheme of the embodiment of the invention, the digital image can be output to the external film reading device with larger display area so as to adapt to various display environments.

In one embodiment of the invention, cells in the selected state may be displayed in a manner that is distinguishable from cells that do not acquire the selected state; for example, the displayed size of cells in the selected state is larger than the displayed size of cells not in the selected state; or, the cell in the selected state has suggestive characters, symbols or graphics, for example, a graphic element surrounding the cell in the selected state is output to a screen to prompt a user that the cell in the graphic element is in a focused state, so that the cell is convenient for a beginner to use. In particular, the graphical elements may have a dynamic effect, thereby having a high degree of recognition.

In one embodiment of the invention, the location of the cell in the selected state is at a set location in the screen, such as the center of the screen. By the technical scheme of the embodiment of the invention, when the cells in the selected state are switched, the cells do not need to be searched in a screen, so that the film reading speed of a user is improved.

In one embodiment of the invention, outputting a digital image of a blood sample into a screen comprises: a digital image of all cells in the blood sample is output to a screen. Through the technical scheme shown in the embodiment of the invention, the digital images of all cells can be displayed on the screen, so that medical staff can conveniently count the proportion of the cells with abnormal morphology to all cells.

In one embodiment of the invention, outputting a digital image of a blood sample into a screen comprises: outputting a magnified digital image of a cell of a set type among all types related to the pre-classification to a screen. By the technical scheme shown in the embodiment of the invention, the directional display of the cells of the set types can be realized, so that the medical staff can conveniently review the cells of the set types.

Step 203: selecting at least one cell in the digital image of cells in the blood sample, the selected at least one cell being in a selected state.

In one embodiment of the invention, outputting the selected state of the at least one cell in the blood sample to a screen comprises: and responding to the human-computer interaction operation, and outputting the selected state corresponding to the target cell of the human-computer interaction operation to the screen. Through the technical scheme shown in the embodiment of the invention, the medical staff can select at least one target cell and directionally output the selected state of the target cell to the screen so as to realize the recheck of the target cell.

In one embodiment of the present invention, the selected state is located at the location of the target cell, which may take the form of, but is not limited to, a central location on the screen. By the technical scheme of the embodiment of the invention, when the cells in the selected state are switched, the cells do not need to be searched in a screen, so that the film reading speed of a user is improved.

In one embodiment of the invention, the selected state of one or more cells can be output at one time according to the one or more cells selected by the man-machine interaction operation. Through the technical scheme of the embodiment of the invention, a plurality of cells in a selected state can be output at one time according to the operation of medical personnel, so that the reading efficiency is improved.

In one embodiment of the invention, outputting the selected state of the at least one cell in the blood sample to a screen comprises: in response to the human-machine interaction, outputting into the screen a selected state that switches between cells of the blood sample. Through the technical scheme shown in the embodiment of the invention, the demonstration of the searching process of the cells in the selected state can be realized.

In one embodiment of the invention, outputting the selected state of the at least one cell in the blood sample to a screen comprises: the cell in the selected state newly obtained after the switching is any cell that has not obtained the selected state, or a cell that satisfies the condition in the cell in the selected state. Through the technical scheme shown in the embodiment of the invention, cells which have not obtained the selected state can be quickly searched and displayed, so that the film reading speed is improved.

In one embodiment of the invention, the selecting according to the condition comprises: when all the cells of one class obtain the selected state, the class which does not obtain the selected state is continuously selected, and the selected state switched in the cells of the corresponding class is output. Through the technical scheme shown in the embodiment of the invention, the cells to be retested can be sequentially detected, and the omission is avoided.

In one embodiment of the invention, the selecting according to the condition comprises: to select based on the arrangement position of cells in the blood sample, cells that are adjacent to the cells that released the selected state and have not acquired the selected state are selected. By the technical scheme of the embodiment of the invention, omission of the cell image to be retested can be avoided in the retest process of the cell image.

In one embodiment of the invention, outputting the selected state of the at least one cell in the blood sample to a screen comprises: and outputting the selected state of at least one cell belonging to the corresponding type in the blood sample to a screen in response to the human-computer interaction operation indicating the pre-classified type. By the technical scheme of the embodiment of the invention, the image retrieval of the pre-classified cells in the selected state can be realized, so that the cell images can be rechecked.

In one embodiment of the invention, outputting the selected state of the at least one cell in the blood sample to a screen comprises: the selected state, which automatically switches between cells of the blood sample, is output to the screen. Through the technical scheme of the embodiment of the invention, medical staff can conveniently observe the switching between blood sample cells in a focusing state so as to improve the speed of reinspection.

In one embodiment of the invention, outputting into a screen a selected state of switching between cells of a blood sample comprises: when the man-machine interaction operation indicates one or more types included in the pre-classification, the selected state is switched in the corresponding one or more types of cells. By the technical scheme shown in the embodiment of the invention, the directional switching of the images of the selected states of the cells of different types can be realized, so that the corresponding information of the cells of different types can be counted conveniently.

In one embodiment of the invention, for the cells of the kind which are not subjected to the re-identification in the blood sample, the selected states of the corresponding cells are output to the screen one by one, and the selected state of each cell is switched after the selected state is kept for the effective time, so that the medical staff can re-identify the outputted cell kind.

Step 204: and receiving and recognizing voice information, and determining the type of the cell in the selected state according to the voice information when the voice information is determined to be used for verifying the type of the cell in the selected state.

In one embodiment of the present invention, the determining the type of the verification of the cell in the selected state according to the voice message includes: and when the pre-classification of the cell in the selected state is output to the screen and the type approved by the voice information is different from the pre-classification of the cell in the selected state, changing the classification of the cell in the selected state into the type approved by the voice information. At this time, when the type approved by the voice message is different from the pre-classification of the cell in the selected state, it is indicated that the previous pre-classification is wrong, and the classification condition of the selected cell can be changed in time by changing and classifying the cell in the selected state to the type approved by the voice message.

In one embodiment of the present invention, the determining the type of the verification of the cell in the selected state according to the voice message includes: and when outputting the pre-classification of the cell in the selected state to the screen and recognizing that the type approved by the voice information is the same as the pre-classification of the cell in the selected state, keeping the pre-classification of the cell in the selected state unchanged. Further, cells in the blood sample that have been classified according to the voice information may also be labeled. At this time, it is recognized that the type approved by the voice information is the same as the pre-classification of the cell in the selected state, which indicates that the previous pre-classification is correct, the processing efficiency can be improved by keeping the pre-classification of the cell in the selected state unchanged, and the corresponding pre-classification process can be recorded, so that the cell analysis device can learn by itself.

In one embodiment of the present invention, the determining the type of the cell under examination from the voice information includes: and when the cell in the selected state is output to the screen and is not pre-classified and the type approved by the voice information is identified, classifying the cell in the selected state to the type approved by the voice information. At this time, since there may be cases such as missing classification in the pre-classification process, when the type specified by the voice information is identified, classifying the cell in the selected state into the type specified by the voice information may classify the cell without pre-classification in time.

In one embodiment of the present invention, the determining the type of the verification of the cell in the selected state according to the voice message includes: when the pre-classification of the cell in the selected state is output to the screen and the voice information is recognized to indicate that the cell in the selected state is switched, the pre-classification of the cell in the selected state is kept unchanged. At the moment, when the voice information is recognized to indicate that the cells in the selected state are switched, the pre-classification of the cells in the selected state is kept unchanged, the adjacent selected cells are switched through one voice instruction, meanwhile, the pre-classification of the corresponding cells is kept unchanged, and the operation speed of cell classification is improved.

In one embodiment of the invention, the speech recognition function may be turned on when the presence of cells in the selected state is recognized before the speech information is recognized. When the cell in the selected state is identified, the voice recognition function is started, so that the interference of other voice information of the user on the type approval of the corresponding cell when the cell in the selected state does not exist can be avoided.

In one embodiment of the invention, the speech recognition function may be turned on when it is recognized that the artificial cell classification procedure is entered before the speech information is recognized. When the selected cell is identified to enter the artificial cell classification flow, the voice recognition function is started, so that the interference of other voice information on the type verification of the corresponding cell when the selected cell exists but does not enter the artificial cell classification flow can be avoided.

In one embodiment of the present invention, the recognizing the voice information includes: comparing the acquired voice information with the preset characteristic parameters of the voice of the approved type; when the acquired voice information corresponds to preset information or instructions, responding to the voice information; and when the acquired voice information does not correspond to the preset information or instruction, not responding to the voice information. Wherein the preset information or instruction may be integrated with the speech recognition device 104. According to the technical scheme of the embodiment, corresponding voice information may appear for many times in the cell verification process, so that parameters of the corresponding voice information can be set in advance, and when the voice information is received, the acquired voice information is compared with the characteristic parameters of preset verification type voice; and when the corresponding parameters are corresponded, the voice information is responded, so that the accuracy of the cell classification operation is improved.

In one embodiment of the present invention, recognizing the speech information to obtain the type of the cell being examined in the selected state comprises: when the pre-classification of the cells in the selected state is output to the screen and the voice operation confirmation pre-classification is recognized, the pre-classification of the cells in the selected state is determined to be an approved category. Through the technical scheme of the embodiment of the invention, the pre-classified type verification of the cells in the selected state can be realized through voice operation.

In one embodiment of the present invention, recognizing the voice message to obtain the type of the cell under examination includes: when the pre-classification of the cell in the selected state is output to the screen and the specific voice operation is recognized, the pre-classification of the cell in the selected state is determined as an approved category. Through the technical scheme of the embodiment of the invention, the pre-classification of the cells to be re-examined can be realized through voice operation.

In one embodiment of the invention, the specific voice operation includes at least one of: confirming pre-classified voice operation; switching the voice operation of the cell in the selected state.

In one embodiment of the present invention, when the type of the cell in the selected state, which is determined by the voice operation, is determined, the classification region in which the cell in the selected state is in the corresponding type is output to the screen. Through the technical scheme of the embodiment of the invention, the cells to be rechecked can be classified through voice operation, so that the manual classification of medical staff is avoided, and the defect that the manual classification is easy to generate errors is avoided.

In one embodiment of the invention, the type of cells that have been verified is cancelled by voice operation. The method comprises the steps of pre-classifying cells in a blood sample, displaying different types of cells in a corresponding classification area, and adjusting the cells in the classification area according to voice operation. Through the technical scheme shown in the embodiment of the invention, cells in each classification area can be adjusted according to voice operation, so that the accuracy of cell classification is improved, and the accuracy of cell classification is improved.

In one embodiment of the invention, the method further comprises:

after the cell types are verified through the voice information, the classification statistical information of the cells in the blood sample is output, so that the user can accurately know the classification condition of the cells in the blood sample.

In one embodiment of the present invention, when it is determined that the voice information is for counting the number of cells in the blood sample, it is determined to count the number of cells in the blood sample based on the voice information. The determining from the speech information to count the number of cells in the blood sample may include: (1) The image of the blood sample is divided into a plurality of counting units with the same area, and each of the divided counting units is numbered. (2) The statistical cells with corresponding numbers are selected by the processing device 103, a voice instruction for representing the cell number information is sent to the voice recognition device 104, and furthermore, a statistical cell with a certain number can also be selected through the corresponding voice instruction. (3) The voice recognition device 104 recognizes the cell number information represented by the corresponding voice command, and fills the cell number information into the statistical cells with corresponding numbers to complete the statistics of the cell number. Therefore, in the process of counting the number of the cells through the voice command, the user does not need to perform manual operation, the whole counting process is controlled and completed by the voice command, and the operation burden of the user is reduced.

Step 205: the type of the cell's nucleation in the selected state is output or stored.

Fig. 3 is a schematic diagram showing an alternative configuration of a cell analyzer according to an embodiment of the present invention, and as shown in fig. 3, a block diagram showing an alternative configuration of a cell analyzer according to an embodiment of the present invention will be described below with reference to blocks in fig. 3.

A receiving part 301 for receiving one or more smears at a time.

Smear 302, stage 303, first objective 304, second objective 305, third objective 306, ocular 307, digital imaging device 308.

Among them, the digital imaging device 308 includes: a first objective lens 304, a second objective lens 305, a third objective lens 306, an eyepiece lens 307, and a digital camera 310.

And a voice recognition device 309 configured to recognize voice information and determine the type of the cells in the selected state, which is determined by the voice operation, wherein the voice recognition device 309 may be disposed in the digital imaging device 308.

Fig. 4A is a schematic diagram illustrating an image display in the cell analysis method according to the embodiment of the present invention, as shown in fig. 4A, the image of the cells in the plurality of fields of the smear can be output to the display area at one time, and the output classification condition of the cells can be verified and corrected by voice operation. Through the technical scheme shown in the embodiment of the invention, medical staff can conveniently observe the images of the cells in a plurality of visual fields of the smear in one display area at one time, so that the statistics of the proportion of diseased cells is more convenient, and meanwhile, the cells which are wrongly classified can be reclassified through voice operation.

Fig. 4B is a schematic diagram illustrating a cell counting operation performed by the cell analyzer according to the embodiment of the present invention, and as shown in fig. 4B, when the number of Platelets (PLTs) can be counted by the cell analyzer, first, an image of platelet cells in a blood sample is divided into a plurality of counting units having the same area, and each of the divided counting units is numbered. As shown in fig. 4B, the image of the platelet cells of the blood sample was divided into 16 counting regions having the same area, and the number of platelet cells in each region was counted.

Fig. 4C is a schematic diagram of the cell analysis device according to the embodiment of the present invention, as shown in fig. 4C, when the cell analysis device can count the number of Platelets (PLTs), the processing device selects the corresponding numbered statistical cells, and sends a voice command representing platelet cell number information to the voice recognition device. And the voice recognition device recognizes the cell number information represented by the corresponding voice command and fills the cell number information into the statistical cells with corresponding numbers so as to complete the statistics of the platelet cell number.

Fig. 5 is an alternative structure diagram of the cell analysis apparatus provided in the embodiment of the present invention, and as shown in fig. 5, the cell analysis apparatus 500 may be a portable analyzer, a medical device with a cell sorting function, or the like. The cell analyzer 500 shown in fig. 5 includes: at least one processor 501, memory 502, at least one network interface 504, and a user interface 503. The various components in the cell analysis device 500 are coupled together by a bus system 505. It is understood that the bus system 505 is used to enable connection communications between these components. The bus system 505 includes a power bus, a control bus, and a status signal bus in addition to a data bus. For clarity of illustration, however, the various buses are labeled as bus system 505 in FIG. 5.

The user interface 503 may include a display, a keyboard, a mouse, a trackball, a click wheel, a key, a button, a touch pad, a touch screen, or the like, among others.

It will be appreciated that the memory 502 can be either volatile memory or nonvolatile memory, and can include both volatile and nonvolatile memory. Among them, the nonvolatile Memory may be a Read Only Memory (ROM), a Programmable Read Only Memory (PROM), an Erasable Programmable Read-Only Memory (EPROM), an Electrically Erasable Programmable Read-Only Memory (EEPROM), a magnetic random access Memory (FRAM), a magnetic random access Memory (Flash Memory), a magnetic surface Memory, an optical Disc, or a Compact Disc Read-Only Memory (CD-ROM); the magnetic surface storage may be disk storage or tape storage. Volatile Memory can be Random Access Memory (RAM), which acts as external cache Memory. By way of illustration and not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), synchronous Static Random Access Memory (SSRAM), dynamic Random Access Memory (DRAM), synchronous Dynamic Random Access Memory (SDRAM), double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM), enhanced Synchronous Dynamic Random Access Memory (ESDRAM), enhanced Synchronous Dynamic Random Access Memory (Enhanced Synchronous Dynamic Random Access Memory), synchronous linked Dynamic Random Access Memory (DRAM, synchronous Link Dynamic Random Access Memory), direct Memory (DRmb Random Access Memory). The memory 502 described in connection with the embodiments of the invention is intended to comprise these and any other suitable types of memory.

Memory 502 in embodiments of the present invention includes, but is not limited to: the ternary content addressable memory, static random access memory, can store a wide variety of data such as cell images, cell classification information, voice operations, etc. to support the operation of the cell analysis device 500. Examples of such data include: any computer program for operating on the cell analysis apparatus 500, such as an operating system 5021 and application programs 5022, cell images, usage records, cell classification information, and the like. The operating system 5021 includes various system programs, such as a framework layer, a core library layer, a driver layer, and the like, for implementing various basic services and processing hardware-based tasks. The application 5022 may include various applications, such as a client with a cell sorting function, an application, etc., for implementing the photoelectric conversion of the light transmitted through the blood sample and passing through the lens set to form a digital image of the cells in the blood sample; outputting a digital image of the blood sample into a screen; outputting a selected state corresponding to at least one cell in the blood sample to a screen; recognizing voice information, and determining the type of the cell in the selected state, which is approved by voice operation; storing various application services including the type of the cell being examined in the selected state. A program for implementing the cell analysis method according to the embodiment of the present invention may be included in the application program 5022.

The method disclosed by the above-mentioned embodiments of the present invention may be applied to the processor 501, or implemented by the processor 501. The processor 501 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the method may be implemented by integrated logic circuits of hardware or operations in software in the processor 501. The Processor 501 may be a general purpose Processor, a Digital Signal Processor (DSP), or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, etc. Processor 501 may implement or perform the methods, steps, and logic blocks disclosed in embodiments of the present invention. A general purpose processor may be a microprocessor or any conventional processor or the like. The steps of the method disclosed by the embodiment of the invention can be directly implemented by a hardware decoding processor, or can be implemented by combining hardware and software modules in the decoding processor. The software modules may be located in a storage medium that is located in the memory 502, and the processor 501 reads the information in the memory 502 and performs the steps of the aforementioned methods in combination with its hardware.

In an exemplary embodiment, the cell analysis Device 500 may be implemented by one or more Application Specific Integrated Circuits (ASICs), DSPs, programmable Logic Devices (PLDs), complex Programmable Logic Devices (CPLDs), field Programmable Gate Arrays (FPGAs), general purpose processors, controllers, micro Controllers (MCUs), microprocessors (microprocessors), or other electronic components for performing the cell analysis method.

In an exemplary embodiment, embodiments of the invention also provide a computer-readable storage medium, such as the memory 502, comprising a computer program executable by the processor 501 of the cell analysis apparatus 500 to perform the aforementioned method steps. The computer readable storage medium can be Memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash Memory, magnetic surface Memory, optical disk, or CD-ROM; or may be various devices, such as a portable analyzer, etc., including one or any combination of the above-described memories.

An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, performs: performing photoelectric conversion on the light rays which penetrate through the blood sample and pass through the lens group to form a digital image of cells in the blood sample; outputting a digital image of the blood sample into a screen; outputting a selected state corresponding to at least one cell in the blood sample to a screen; recognizing voice information, and determining the type of the cell in the selected state, which is approved by voice operation; the type of the assay of the cells in the selected state is stored.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, embodiments of the present invention may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including magnetic disk storage, optical storage, and the like) having computer-usable program code embodied therein.

Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program operations. These computer programs may be provided to operate on a processor of a general purpose computer, special purpose computer, embedded processor or other programmable data processing apparatus to produce a machine, such that the operations performed by the processor of the computer or other programmable data processing apparatus produce a means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program operations may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the operations stored in the computer-readable memory produce an article of manufacture including processing means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program operations may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the operations executed on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

The above description is only for the purpose of illustrating the preferred embodiments of the present invention and should not be taken as limiting the scope of the present invention, which is intended to cover any modifications, equivalents, improvements, etc. within the spirit and scope of the present invention.

Claims

1. A cell analysis method applied to a cell analysis apparatus includes:

obtaining a digital image of cells in a blood sample;

outputting a digital image of cells in the blood sample;

selecting a digital image of at least one cell of said blood sample;

receiving voice information;

recognizing the voice information, and determining the verification type of the cell in the selected state according to the voice information when the voice information is determined to be used for verifying the type of the cell in the selected state; wherein, the classification of the cell type comprises the specification of the cell type which is pre-classified or not.

2. The method of claim 1, wherein after said determining a check category of cells in a selected state from said voice message, further comprising: outputting or storing the determined species of the cells in the selected state.

3. The method of claim 1, wherein said outputting a digital image of cells in said blood sample comprises:

outputting the digital image of the cells in the blood sample and the target classification of the cells into a screen;

the recognizing the voice information, and when determining that the voice information is used for determining the type of the cell in the selected state, determining the determined type of the cell in the selected state according to the voice information includes:

and when the type of the voice information approval is judged to be one of the target classifications, determining the approval type of the cell in the selected state according to the voice information.

4. The method of claim 1, wherein said outputting a digital image of said blood sample comprises:

and outputting the digital image of the cells in the blood sample, the target classification information of the cells and the pre-classification information of the cells to a screen.

5. The method of claim 4, wherein the method further comprises:

identifying at least one cell in the digital image of cells in the blood sample prior to selecting the at least one cell in the digital image of cells in the blood sample;

pre-classifying the at least one cell to the target classification information, thereby obtaining pre-classification information for the at least one cell in the digital image of cells in the blood sample.

6. The method of claim 1, wherein said determining a qualifying type of cells in a selected state from said speech information comprises:

outputting pre-classification information of the cell in the selected state to a screen, wherein the type approved by the voice information is different from the pre-classification of the cell in the selected state,

the classification of the cells in the selected state is modified to the class approved by the voice message.

7. The method of claim 6, wherein said outputting to a screen pre-classification information of cells in a selected state comprises: outputting pre-classification information of the cells in the selected state to a screen in the form of a classification region, wherein the classification region is used for representing the types to which the cells belong, and the classification region comprises images of the cells belonging to the corresponding types in the blood sample;

and when the cells in the selected state are determined to be changed into the category approved by the voice information, outputting the cells in the selected state to a screen, wherein the cells in the selected state are changed from the classification area corresponding to the pre-classification to the classification area in the approved category.

8. The method of claim 1, wherein said determining from said voice information the type of approval of the cell in the selected state comprises:

when the pre-classification information of the cell in the selected state is output to the screen and the type approved by the voice information is the same as the pre-classification of the cell in the selected state,

maintaining the pre-classification of the cells in the selected state unchanged.

9. The method of claim 8, wherein when it is determined that the pre-classification of the cell in the selected state is unchanged, the classification region where the cell in the selected state of the screen output is located is kept unchanged; the classification region includes images of cells belonging to the respective category in the blood sample.

10. The method of any of claims 1-7, wherein the method further comprises:

cells of which the species has been determined from the speech information are labeled.

11. The method of any one of claims 1-7, wherein said determining the type of the selected cell based on the speech information comprises:

when the cells in the selected state are output to the screen without being pre-classified and the class approved by the voice message is recognized,

and classifying the cells in the selected state into the category approved by the voice information.

12. The method according to claim 11, wherein when it is determined that the cell in the selected state is classified into the category specified by the voice message, outputting a classification region in which the cell in the selected state is in the specified category to a screen; the classification region includes images of cells belonging to the respective category in the blood sample.

13. The method of claim 1, wherein said determining a nucleated species of the cell in the selected state from the speech information comprises:

when the digital image of the cell in the selected state is output to the screen and the voice information indicating switching of the cell in the selected state is recognized,

switching cells in a selected state in response to the voice information;

wherein switching the cells in the selected state comprises: the cell in the selected state is switched from the selected state to the unselected state, and the other cell is switched from the unselected state to the selected state.

14. The method of claim 1, wherein the method further comprises:

the kind of the cell identification in the blood sample is cancelled through voice operation.

15. The method of claim 1, wherein the method further comprises:

prior to the recognition of the speech information in question,

and when the cells in the selected state exist or enter the artificial cell classification process, starting the voice recognition function.

16. The method of claim 1, wherein the recognizing speech information comprises:

in the process of artificial cell classification, the operation of recognizing voice information is continuously performed, or,

and performing voice information recognition operation when the selected state of the cell is output.

17. The method of claim 1, wherein the identifying the voice information comprises:

comparing the acquired voice information with preset information or instructions;

when the acquired voice information corresponds to preset information or instructions, responding to the voice information;

and when the acquired voice information does not correspond to the preset information or instruction, not responding to the voice information.

18. The method of claim 1, wherein said selecting at least one cell in the digital image of cells in the blood sample comprises:

selecting at least one cell in the digital image of cells in the blood sample in response to a human-computer interaction; alternatively, the first and second liquid crystal display panels may be,

switching cells in a selected state;

19. The method of claim 18, wherein,

the cell which newly obtains the selected state after switching is any cell which does not obtain the selected state, or the cell which meets the preset condition in the cell which does not obtain the selected state;

the cells meeting the preset conditions comprise cells belonging to a preset selected type or cells meeting a preset positional relationship.

20. The method of claim 1, further comprising: automatically switching cells in a selected state;

the automatically switching cells in a selected state comprises: switching the current cell in the selected state from the selected state to a non-selected state, and switching another cell from the non-selected state to the selected state according to a preset sequence; a cell in the selected state has a selected designation or information indicating that the cell is currently selected.

21. The method of claim 1, wherein the method further comprises:

and after the cell types are verified through voice information, updating or outputting the classification statistical information of the cells in the blood sample.

22. The method of claim 1, wherein the method further comprises:

when it is determined that the voice information is for counting the number of cells of the selected area of the digital image of the blood sample, recording the number of cells of the selected area based on the voice information.

23. A cell analysis device, comprising:

processing means configured to determine an approval type of the cell in the selected state from the voice information when it is determined that the voice information is for approving the type of the cell in the selected state; wherein, the determining the category comprises determining the category of the cell which is pre-classified or not classified.

24. The cell analysis apparatus according to claim 23,

the voice recognition device is further configured to output the approved species of the cell in the selected state;

a storage device configured to store the determined species of the cells in the selected state.

25. The cell analysis apparatus according to claim 23,

the display output device is also configured to output the digital image of the cells in the blood sample and the target classification information of the cells to a screen;

and the voice recognition device is configured to determine the approved type of the cell in the selected state according to the voice information when judging that the approved type of the voice information is one of the target classifications.

26. The cell analysis apparatus according to claim 23,

the display output device is also configured to output the digital image of the cells in the blood sample, the target classification information of the cells and the pre-classification information of the cells to a screen;

the voice information is used for characterizing the matching relation between the pre-classification information for verifying the cells and the target classification information of the cells.

27. The cell analysis apparatus according to claim 26,

the processing device further configured to identify at least one cell in the digital image of cells in the blood sample prior to selecting the at least one cell in the digital image of cells in the blood sample;

the processing device is further configured to pre-classify the at least one cell to the target classification information, thereby obtaining pre-classification information for the at least one cell in the digital image of cells in the blood sample.

28. The cell analysis apparatus according to claim 23,

the voice recognition device is further configured to change the classification of the cell in the selected state to the classification of the cell in the selected state when the pre-classification information of the cell in the selected state is output on the screen and the classification of the cell in the selected state is different from the pre-classification of the cell in the selected state.

29. The cell analysis apparatus according to claim 28,

the voice recognition device is further configured to output the pre-classification information of the cells in the selected state to a screen, and the pre-classification information comprises: outputting pre-classification information of cells in a selected state to a screen in the form of a classification region, wherein the classification region is used for representing the types of the cells belonging to the classification region, and the classification region comprises images of the cells belonging to the corresponding types in the blood sample;

when the cells in the selected state are determined to be changed into the category approved by the voice information, the cells in the selected state are output to a screen, and the classified areas corresponding to the pre-classification are changed into the classified areas in the approved category; the classification region includes images of cells belonging to the respective category in the blood sample.

30. The cell analysis apparatus according to claim 23,

the voice recognition device is also configured to keep the pre-classification of the cell in the selected state unchanged when the pre-classification information of the cell in the selected state is output to the screen and the type approved by the voice information is the same as the pre-classification of the cell in the selected state.

31. The cell analysis apparatus according to claim 30,

the voice recognition device is further configured to output the classification area of the cell in the selected state to the screen to be kept unchanged when the pre-classification of the cell in the selected state is determined to be unchanged; the classification region includes images of cells belonging to the respective category in the blood sample.

32. The cell analysis device according to any one of claims 23 to 29,

the voice recognition device is also configured to mark the mesocyte with the type which is determined according to the voice information.

33. The cell analysis device according to any one of claims 23 to 29,

the voice recognition device is further configured to classify the cell in the selected state into the category approved by the voice information when the cell in the selected state is not pre-classified and the category approved by the voice information is recognized.

34. The cell analysis apparatus according to claim 33,

the voice recognition device is further configured to output a classification area of the cell in the selected state in the determined type to a screen when the cell in the selected state is determined to be classified into the type determined by the voice information; the classification region includes images of cells belonging to the respective category in the blood sample.

35. The cell analysis apparatus according to claim 23,

the voice recognition device is also configured to output the digital image of the cell in the selected state to the screen, and when the voice information indicating that the cell in the selected state is switched is recognized,

the display output device is also configured to respond to the voice information and switch the cells in the selected state;

wherein switching the cells in the selected state comprises: the current cell in the selected state is switched from the selected state to the unselected state, and the other cell in the digital image is switched from the unselected state to the selected state.

36. The cell analysis apparatus according to claim 23,

the voice recognition device is further configured to cancel the type of cell identification in the blood sample through voice operation.

37. The cell analysis apparatus according to claim 23,

the speech recognition device, further configured to, prior to recognizing the speech information,

and when the cells in the selected state enter the artificial cell classification process, starting the voice recognition function.

38. The cell analysis apparatus according to claim 23,

the voice recognition apparatus is further configured to continue the operation of recognizing the voice information during the classification of the artificial cells, or,

the voice recognition device is also configured to perform a voice information recognition operation when the selected state of the cell is output.

39. The cell analysis apparatus according to claim 23,

the voice recognition device is also configured to compare the acquired voice information with the preset characteristic parameters of the voice of the approved type;

the voice recognition device is also configured to respond to the voice information when the acquired voice information corresponds to preset information or instructions;

the voice recognition device is further configured to not respond to the voice information when the acquired voice information does not correspond to preset information or instructions.

40. The cell analysis apparatus according to claim 23,

the display output device is further configured to respond to human-computer interaction operation and select at least one cell in the digital image of the cell in the blood sample;

the display output device is also configured to respond to human-computer interaction operation and switch the cells in the selected state;

41. The cell analysis apparatus according to claim 40, wherein,

the cell which newly acquires the selected state after switching is any cell which does not acquire the selected state, or the cell which meets the preset condition in the cell which does not acquire the selected state;

42. The cell analysis apparatus according to claim 23,

the display output device is further configured to output a selected state of automatic switching between cells of the blood sample into a screen;

43. The cell analysis apparatus according to claim 23,

the display output device is also configured to update or output the classification statistical information of the cells in the blood sample after the cell types are determined through the voice information.

44. The cell analysis apparatus according to claim 23,

the voice recognition device is configured to determine that the voice information is used for counting the number of cells in the selected area of the digital image of the blood sample, and record the number of cells in the selected area according to the voice information.

45. The cell analysis apparatus according to claim 23, wherein the cell analysis apparatus further comprises:

an imaging device configured to capture cells in the blood sample to form a digital image of the cells in the blood sample;

the smear dyeing device is configured to prepare a blood sample into a cell smear and push the smear to the imaging device.

46. A cell analysis apparatus, comprising:

a memory for storing executable instructions;

a processor for executing the executable instructions stored in the memory to perform the cell analysis method of any one of claims 1 to 22.

47. A storage medium storing an executable program for causing a processor to execute the executable program to implement the cell analysis method according to any one of claims 1 to 22.