Cerebrospinal fluid cell marking method and device, computer equipment and storage medium
By using square bounding boxes and a classification model to display cell type names and color information in cerebrospinal fluid cell images, the problem of cell identification errors caused by different definitions in different regions is solved, and accurate cerebrospinal fluid cell labeling is achieved.
Patent Information
- Application Number
- CN202511038828.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-28
- Publication Date
- 2025-11-14
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
In the existing technology, different regions and countries have different definitions of the names of cerebrospinal fluid cells, which leads to cell identification errors or misunderstandings and affects the accuracy of cerebrospinal fluid cell labeling.
By acquiring cerebrospinal fluid cell images and displaying the entire image, cells are located using square marker boxes. Combined with a preset classification model and mapping relationship, cell type names and color information are displayed to ensure that each cell has a unique marker.
This effectively avoids cell recognition errors and comprehension conflicts, improving the accuracy and consistency of cerebrospinal fluid cell labeling.
Smart Images
Figure CN120953984A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of cerebrospinal fluid cell labeling technology, and in particular to cerebrospinal fluid cell labeling methods, devices, computer equipment, and storage media. Background Technology
[0002] Cerebrospinal fluid (CSF) cells are mainly produced by the central nervous system and include astrocytes, microglia, lymphocytes, phagocytes, granulocytes, and giant cells. These cells play a role in maintaining a stable CSF environment and helping to protect neurons from damage. When an abnormal increase occurs, it may cause diseases such as meningitis and cerebral edema, leading to symptoms such as headache and fever. In addition, it may also be accompanied by nausea, vomiting, and changes in mental status. In order to diagnose CSF-related diseases, it is usually necessary to review CSF cell images to classify and count CSF cells. During the review of CSF cell images, it is usually necessary to label CSF cells in order to track the function and behavior of specific cells.
[0003] In the field of cerebrospinal fluid cell labeling, existing technologies typically use the outline of cerebrospinal fluid cells to mark their location and display their names around the outline. However, different regions, countries, and hospitals may define different names for the same type of cerebrospinal fluid cells. Labeling cerebrospinal fluid cells using only their names can easily lead to cell identification errors or misunderstandings. Summary of the Invention
[0004] In view of the aforementioned existing problems, the present invention is proposed.
[0005] Therefore, the present invention provides a method for labeling cerebrospinal fluid cells to solve the problem that in the prior art, the location of cerebrospinal fluid cells is usually marked by the outline of the cerebrospinal fluid cells and the name of the cerebrospinal fluid cells is displayed around the outline of the cerebrospinal fluid cells. However, different regions, countries and hospitals may define different names for the same type of cerebrospinal fluid cells. Labeling cerebrospinal fluid cells by only using the name of the cerebrospinal fluid cells can easily cause problems such as cell identification errors or misunderstandings.
[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution:
[0007] In a first aspect, the present invention provides a method for labeling cerebrospinal fluid cells, comprising:
[0008] Acquire cerebrospinal fluid cell images and display the cerebrospinal fluid cell images in their entirety. The cerebrospinal fluid cell images are obtained by scanning a cerebrospinal fluid cell smear in its entirety.
[0009] In response to the cell selection operation of the cerebrospinal fluid cell image, cell detection is performed on the selected area, and the cells detected in the selected area are selected and located using a square marker box, wherein the vertical distance between each side of the square marker box and the center of the cell is a preset distance;
[0010] The cells detected in the selected region are classified using a preset classification model to obtain the cell classification information;
[0011] The color information corresponding to the classification information is obtained based on a preset mapping relationship;
[0012] The color blocks corresponding to the color information and the type names corresponding to the cells are displayed sequentially above the square marker box.
[0013] In a preferred embodiment of the cerebrospinal fluid cell labeling method of the present invention, the acquisition of cerebrospinal fluid cell images specifically includes:
[0014] A full-slide scan of a cerebrospinal fluid cell smear is performed using a scanning device to obtain a digital image containing the distribution of all cells.
[0015] The full-screen display refers to presenting the complete cerebrospinal fluid cell image obtained from the scan in a scalable format on the display interface for users to view and select.
[0016] In a preferred embodiment of the cerebrospinal fluid cell labeling method of the present invention, the response to the cell selection operation specifically includes:
[0017] When a user selects a region of interest on the displayed cerebrospinal fluid cell image using a mouse or touch, the system automatically identifies all cells contained within that selected region.
[0018] The cell detection method uses an image recognition algorithm to scan and analyze a selected area to locate the position information of each cell.
[0019] In a preferred embodiment of the cerebrospinal fluid cell labeling method of the present invention, the step of using a square marking frame for box selection and positioning specifically includes:
[0020] For each detected cell, a square marking area is formed by extending outwards from its geometric center.
[0021] The preset distance setting must ensure that an appropriate gap is maintained between the marker box and the cell outline so that the cell morphology is clearly visible.
[0022] In a preferred embodiment of the cerebrospinal fluid cell labeling method of the present invention, the classification using a preset classification model specifically includes:
[0023] Input the cell image region within the square bounding box into a pre-trained multi-level classification model;
[0024] The classification model outputs primary, secondary, and tertiary classification information of cells in sequence, corresponding to the major category, subcategory, and specific type of cells, respectively.
[0025] In a preferred embodiment of the cerebrospinal fluid cell labeling method of the present invention, the step of obtaining color information based on a preset mapping relationship specifically includes:
[0026] The system has a built-in table that maps classification information to color codes, where each level of classification information corresponds to a specific color code.
[0027] The color information includes three levels of color identifiers, each corresponding to a three-level classification result of the cell.
[0028] In a preferred embodiment of the cerebrospinal fluid cell labeling method of the present invention, the display color patch and type name specifically include:
[0029] Above the square marker box, three levels of color-coded blocks are arranged sequentially, representing the primary, secondary, and tertiary classifications of cells, respectively.
[0030] Display the full cell type name after the color-coded block;
[0031] The arrangement of the color identifier blocks and type names ensures a fixed relative position with the marker boxes.
[0032] In a second aspect, the present invention provides a cerebrospinal fluid cell labeling device, comprising:
[0033] The module includes an acquisition module, a response module, a classification module, a mapping module, and a display module.
[0034] The acquisition module is used to acquire cerebrospinal fluid cell images and display the cerebrospinal fluid cell images in their entirety; the cerebrospinal fluid cell images are obtained by scanning a cerebrospinal fluid cell smear in its entirety.
[0035] The response module is configured to respond to a cell selection operation on the cerebrospinal fluid cell image by performing cell detection on the selected area and locating the detected cells in the selected area using a square marker box; the vertical distance between each side of the square marker box and the center of the cell is a preset distance.
[0036] The classification module is used to classify the cells detected in the selected area using a preset classification model to obtain the classification information of the cells;
[0037] The mapping module is used to obtain the color information corresponding to the classification information based on a preset mapping relationship;
[0038] The display module is used to sequentially display the color blocks corresponding to the color information and the type names corresponding to the cells above the square marker box.
[0039] Thirdly, the present invention provides a computer device including a memory and a processor, wherein the memory stores a computer program, wherein the computer program, when executed by the processor, implements any step of the cerebrospinal fluid cell labeling method as described in the first aspect of the present invention.
[0040] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein, when the computer program is executed by a processor, it implements any step of the cerebrospinal fluid cell labeling method as described in the first aspect of the present invention.
[0041] The beneficial effects of this invention are as follows: by using square marking boxes to mark the location of cerebrospinal fluid cells, and by using the cell type name and color block corresponding to the color information to represent the cerebrospinal fluid cell type, the color block corresponding to the color information and the cell type name are displayed sequentially above the square marking box, so that each type of cerebrospinal fluid cell has a unique mark, effectively avoiding the situation of cerebrospinal fluid cell interpretation conflict. Attached Figure Description
[0042] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0043] Figure 1 This is a flowchart of the cerebrospinal fluid cell labeling method in Example 1.
[0044] Figure 2 This is a schematic diagram of the cerebrospinal fluid cell labeling device in Example 1.
[0045] Figure 3 This is a schematic diagram of cerebrospinal fluid cell labeling in Example 1.
[0046] Figure 4 This is a schematic diagram of the computer equipment in Example 1.
[0047] Figure 5 This is a diagram illustrating the application scenario of the cerebrospinal fluid cell labeling method in Example 1. Detailed Implementation
[0048] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
[0049] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.
[0050] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.
[0051] Example 1, referring to Figure 1 - Figure 4 This is the first embodiment of the present invention, which provides a method for labeling cerebrospinal fluid cells, including the following steps:
[0052] S1. Acquire cerebrospinal fluid cell images and display the cerebrospinal fluid cell images in their entirety. The cerebrospinal fluid cell images are obtained by scanning the entire cerebrospinal fluid cell smear.
[0053] Furthermore, obtaining images of cerebrospinal fluid cells specifically includes:
[0054] A full-slide scan of a cerebrospinal fluid cell smear is performed using a scanning device to obtain a digital image containing the distribution of all cells.
[0055] The full-screen display refers to presenting the complete cerebrospinal fluid cell image obtained from the scan in a scalable format on the display interface for users to view and select.
[0056] It should be noted that the entire cerebrospinal fluid cell image is displayed, allowing users to select the region of interest.
[0057] S2. In response to the cell selection operation for the cerebrospinal fluid cell image, cell detection is performed on the selected area, and the cells detected in the selected area are selected and located using a square marker box, wherein the vertical distance between each side of the square marker box and the center of the cell is a preset distance.
[0058] Furthermore, the specific responses to cell selection operations include:
[0059] When a user selects a region of interest on the displayed cerebrospinal fluid cell image using a mouse or touch, the system automatically identifies all cells contained within that selected region.
[0060] The cell detection involves scanning and analyzing a selected area using an image recognition algorithm to locate the position information of each cell within it.
[0061] Using a square marker box for selection and positioning specifically includes:
[0062] For each detected cell, a square marking area is formed by extending outwards from its geometric center.
[0063] The preset distance setting must ensure that an appropriate gap is maintained between the marker box and the cell outline so that the cell morphology is clearly visible;
[0064] When a user is interested in a certain area, they can select a region in the cerebrospinal fluid cell image. In response to the cell selection operation, the server detects the selected region and locates the cells detected in the selected region using square marker boxes. There is a certain distance between the square marker box and the outline of the cerebrospinal fluid cells, so that the user can observe the outline of the cerebrospinal fluid cells more clearly. In addition, the vertical distance between each side of the square marker box and the center of the cell in the cerebrospinal fluid cell marking method provided in this application can be set according to the actual scenario to ensure that there is a certain distance between the square marker box and the outline of all cerebrospinal fluid cells in the selected area.
[0065] It should be noted that the size of the square marking frame needs to take into account both cell morphology characteristics and observation requirements. It must ensure that the marking frame completely encompasses the target cell and its surrounding feature area, while avoiding an excessively large marking frame that could affect the identification of adjacent cells. In practical applications, the preset distance can be dynamically adjusted according to cell type, magnification, and user preferences to ensure optimal cell observation and marking effects in different application scenarios. Furthermore, the design of the square marking frame facilitates rapid system calculation and positioning, which is beneficial for subsequent classification processing and marking display operations.
[0066] S3. Classify the cells detected in the selected area using a preset classification model to obtain cell classification information;
[0067] Furthermore, classification using a pre-defined classification model specifically includes:
[0068] Input the cell image region within the square bounding box into a pre-trained multi-level classification model;
[0069] The classification model outputs primary, secondary, and tertiary classification information of cells in sequence, corresponding to the major category, subcategory, and specific type of cells, respectively.
[0070] It should be noted that a preset multi-level classification model can be used to classify the cells detected in the selected area, thereby obtaining multi-level classification information of the cells and making the cell classification more detailed. For example, a preset three-level classification model can be used to classify the cells detected in the selected area, thereby obtaining the primary, secondary and tertiary classification information of the cells.
[0071] S4. Obtain the color information corresponding to the classification information based on the preset mapping relationship;
[0072] Furthermore, the system has a built-in table that maps classification information to color codes, where each level of classification information corresponds to a specific color code.
[0073] The color information includes three levels of color identifiers, which correspond to the three-level classification results of cells;
[0074] It should be noted that the preset mapping relationship is the pre-set correspondence between cell categories and colors. Based on the preset mapping relationship, the color information corresponding to the classification information can be obtained. It can be understood that in the preset mapping relationship, different cell categories correspond to different colors.
[0075] S5. Display the color blocks corresponding to the color information and the type names corresponding to the cells in sequence above the square marker box;
[0076] Furthermore, the display of color blocks and type names specifically includes:
[0077] Above the square marker box, three levels of color-coded blocks are arranged sequentially, representing the primary, secondary, and tertiary classifications of cells, respectively.
[0078] Display the full cell type name after the color-coded block;
[0079] The arrangement of the color identifier blocks and type names ensures a fixed relative positional relationship with the marker boxes;
[0080] It should be noted that, with Figure 3 Taking mature neutrophils as an example, mature neutrophils are a secondary classification, and the primary classification information is granulocytes. Based on the preset mapping relationship, the color information corresponding to the primary classification information can be determined as color one. The secondary classification information is mature neutrophils, and the color information corresponding to the secondary classification information can be determined as color two. Then, the color blocks corresponding to color one and color two, and the type name of mature neutrophils, are displayed sequentially above the square marker box. The final effect is as follows: Figure 3 As shown.
[0081] This embodiment also provides a cerebrospinal fluid cell labeling device, including:
[0082] The module includes an acquisition module, a response module, a classification module, a mapping module, and a display module.
[0083] The acquisition module is used to acquire cerebrospinal fluid cell images and display the cerebrospinal fluid cell images in their entirety; the cerebrospinal fluid cell images are obtained by scanning a cerebrospinal fluid cell smear in its entirety.
[0084] The response module is configured to respond to a cell selection operation on the cerebrospinal fluid cell image by performing cell detection on the selected area and locating the detected cells in the selected area using a square marker box; the vertical distance between each side of the square marker box and the center of the cell is a preset distance.
[0085] The classification module is used to classify the cells detected in the selected area using a preset classification model to obtain the classification information of the cells;
[0086] The mapping module is used to obtain the color information corresponding to the classification information based on a preset mapping relationship;
[0087] The display module is used to sequentially display the color blocks corresponding to the color information and the type names corresponding to the cells above the square marker box.
[0088] The aforementioned cerebrospinal fluid cell labeling device acquires cerebrospinal fluid cell images and displays the entire image. The cerebrospinal fluid cell image is obtained by scanning a cerebrospinal fluid cell smear. In response to a cell selection operation on the cerebrospinal fluid cell image, it detects cells in the selected area and locates the detected cells in the selected area using a square label box. The vertical distance between each side of the square label box and the center of the cell is a preset distance. The device classifies the detected cells in the selected area using a preset classification model to obtain cell classification information. It obtains the color information corresponding to the classification information based on a preset mapping relationship. The color block corresponding to the color information and the cell type name are displayed sequentially above the square label box.
[0089] This embodiment also provides a computer device suitable for the cerebrospinal fluid cell labeling method, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the cerebrospinal fluid cell labeling method as proposed in the above embodiment.
[0090] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.
[0091] This embodiment also provides a storage medium on which a computer program is stored. When executed by a processor, the program implements the cerebrospinal fluid cell labeling method as proposed in the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.
[0092] In summary, this invention uses square marker boxes to mark the location of cerebrospinal fluid cells and uses a combination of cell type names and color blocks corresponding to color information to represent cerebrospinal fluid cell types. The color blocks corresponding to color information and cell type names are displayed sequentially above the square marker boxes, so that each type of cerebrospinal fluid cell has a unique marker, effectively avoiding cerebrospinal fluid cell interpretation conflicts.
[0093] Example 2, refer to Figure 5 This is the second embodiment of the present invention, which provides an application scenario for the cerebrospinal fluid cell labeling method, specifically including:
[0094] Both the cerebrospinal fluid detection device 101 and the scanner 102 can transmit data via a network;
[0095] The scanner 102 is used to scan the cerebrospinal fluid cell smear to obtain cerebrospinal fluid cell images and transmit the cerebrospinal fluid cell images to the cerebrospinal fluid detection device 101.
[0096] After the cerebrospinal fluid detection device 101 acquires the cerebrospinal fluid cell image, it displays the entire cerebrospinal fluid cell image. In response to the cell selection operation of the cerebrospinal fluid cell image, the cerebrospinal fluid detection device 101 performs cell detection on the selected area and uses a square marker box to select and locate the cells detected in the selected area.
[0097] The vertical distance between each side of the square marker frame and the center of the cell is a preset distance;
[0098] The cells detected in the selected area are classified using a pre-defined classification model to obtain the cell classification information;
[0099] Obtain the color information corresponding to the classification information based on the preset mapping relationship;
[0100] The color blocks corresponding to the color information and the type names corresponding to the cells are displayed sequentially above the square marker box.
[0101] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.
Claims
1. A method for labeling cerebrospinal fluid cells, characterized in that: include: Acquire cerebrospinal fluid cell images and display the cerebrospinal fluid cell images in their entirety. The cerebrospinal fluid cell images are obtained by scanning a cerebrospinal fluid cell smear in its entirety. In response to the cell selection operation of the cerebrospinal fluid cell image, cell detection is performed on the selected area, and the cells detected in the selected area are selected and located using a square marker box, wherein the vertical distance between each side of the square marker box and the center of the cell is a preset distance; The cells detected in the selected region are classified using a preset classification model to obtain the cell classification information; The color information corresponding to the classification information is obtained based on a preset mapping relationship; The color blocks corresponding to the color information and the type names corresponding to the cells are displayed sequentially above the square marker box.
2. The cerebrospinal fluid cell labeling method as described in claim 1, characterized in that: The acquisition of cerebrospinal fluid cell images specifically includes: A full-slide scan of a cerebrospinal fluid cell smear is performed using a scanning device to obtain a digital image containing the distribution of all cells. The full-screen display refers to presenting the complete cerebrospinal fluid cell image obtained from the scan in a scalable format on the display interface for users to view and select.
3. The cerebrospinal fluid cell labeling method as described in claim 2, characterized in that: The response to the cell selection operation specifically includes: When a user selects a region of interest on the displayed cerebrospinal fluid cell image using a mouse or touch, the system automatically identifies all cells contained within that selected region. The cell detection method uses an image recognition algorithm to scan and analyze a selected area to locate the position information of each cell.
4. The cerebrospinal fluid cell labeling method as described in claim 3, characterized in that: The specific steps of using a square marker box for selection and positioning include: For each detected cell, a square marking area is formed by extending outwards from its geometric center. The preset distance setting must ensure that an appropriate gap is maintained between the marker box and the cell outline so that the cell morphology is clearly visible.
5. The cerebrospinal fluid cell labeling method as described in claim 4, characterized in that: The classification using a preset classification model specifically includes: Input the cell image region within the square bounding box into a pre-trained multi-level classification model; The classification model outputs primary, secondary, and tertiary classification information of cells in sequence, corresponding to the major category, subcategory, and specific type of cells, respectively.
6. The cerebrospinal fluid cell labeling method as described in claim 5, characterized in that: The acquisition of color information based on a preset mapping relationship specifically includes: The system has a built-in table that maps classification information to color codes, where each level of classification information corresponds to a specific color code. The color information includes three levels of color identifiers, each corresponding to a three-level classification result of the cell.
7. The cerebrospinal fluid cell labeling method as described in claim 6, characterized in that: The display color blocks and type names specifically include: Above the square marker box, three levels of color-coded blocks are arranged sequentially, representing the primary, secondary, and tertiary classifications of cells, respectively. Display the full cell type name after the color-coded block; The arrangement of the color identifier blocks and type names ensures a fixed relative position with the marker boxes.
8. A cerebrospinal fluid cell labeling device, based on the cerebrospinal fluid cell labeling method according to any one of claims 1 to 7, characterized in that: include: The module includes an acquisition module, a response module, a classification module, a mapping module, and a display module. The acquisition module is used to acquire cerebrospinal fluid cell images and display the cerebrospinal fluid cell images in their entirety; the cerebrospinal fluid cell images are obtained by scanning a cerebrospinal fluid cell smear in its entirety. The response module is configured to respond to a cell selection operation on the cerebrospinal fluid cell image by performing cell detection on the selected area and locating the detected cells in the selected area using a square marker box; the vertical distance between each side of the square marker box and the center of the cell is a preset distance. The classification module is used to classify the cells detected in the selected area using a preset classification model to obtain the classification information of the cells; The mapping module is used to obtain the color information corresponding to the classification information based on a preset mapping relationship; The display module is used to sequentially display the color blocks corresponding to the color information and the type names corresponding to the cells above the square marker box.
9. A computer device, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the cerebrospinal fluid cell labeling method according to any one of claims 1 to 7.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the cerebrospinal fluid cell labeling method according to any one of claims 1 to 7.