Cerebrospinal fluid cell morphology auditing process method and device, computer equipment and storage medium

Abstract

The invention discloses a cerebrospinal fluid cell morphology auditing process method and device, computer equipment and a storage medium, and relates to the technical field of cerebrospinal fluid cell morphology auditing, and the method comprises the steps: responding to the selection operation of a distribution diagram function module, carrying out the full-piece display of a cerebrospinal fluid cell image, and obtaining a cerebrospinal fluid cell image; the cerebrospinal fluid cell image is an image obtained by performing full scanning on a cerebrospinal fluid cell smear; in response to a frame selection counting button for the cerebrospinal fluid cell image, a cell frame selection interface is provided for a user to frame and select areas needing to be counted, and the cerebrospinal fluid cell image is displayed on the cell frame selection interface; and in response to a frame selection operation of a user, extracting nucleated cells existing in the frame selection area. According to the method, the nucleated cells in the frame selection area on the cerebrospinal fluid cell image are automatically extracted, counted, marked and classified under the distribution diagram function module, so that the target number of cerebrospinal fluid nucleated cells can be quickly and accurately identified.

Description

Technical Field

[0001] This application relates to the field of cerebrospinal fluid cell morphology review technology, and in particular to a cerebrospinal fluid cell morphology review process, method, apparatus, computer equipment, and storage medium. Background Technology

[0002] By reviewing cerebrospinal fluid smears, and based on the specific cell types and corresponding quantities present in the smears, a diagnosis can be made regarding the type and severity of the disease.

[0003] In existing technologies, cerebrospinal fluid (CSF) cell smears are placed on a microscope platform. Doctors use low magnification to observe the entire smear, identifying areas where CSF nucleated cells need to be counted. After locating these areas, high magnification is used to observe, classify, and count the target number of CSF nucleated cells based on their type. The results are recorded and a CSF report is generated. However, manual review of CSF cell images is time-consuming, prone to omissions, and involves prolonged work under a microscope, increasing the risk of fatigue and misjudgment. These factors contribute to the low efficiency of existing CSF cell morphology review processes. 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 reviewing cerebrospinal fluid cell morphology, which solves the problem of low efficiency in the prior art.

[0006] In the first aspect, embodiments of this application provide a method for reviewing the morphology of cerebrospinal fluid cells. The method includes the following steps: in response to the selection operation of the distribution map function module, a full-slice image of cerebrospinal fluid cells is displayed; the cerebrospinal fluid cell image is an image obtained by scanning a full-slice cerebrospinal fluid cell smear.

[0007] In response to the box selection and counting button for the cerebrospinal fluid cell image, a cell selection interface is provided for the user to select the area to be counted, and the cerebrospinal fluid cell image is displayed on the cell selection interface;

[0008] In response to the user's selection operation, the nucleated cells present in the selected area are extracted, and the number of nucleated cells present in the selected area is displayed on the cell selection interface;

[0009] In response to the confirmation button for the selection operation on the cell selection interface, all nucleated cells in the selected area are marked and classified, and the nucleated cells are counted based on their type.

[0010] In response to the selection operation of the cell map function module, the images of all nucleated cells extracted within the selected area and their corresponding types will be displayed for user review.

[0011] A cerebrospinal fluid report is generated based on the results of the review of the nucleated cells.

[0012] In a preferred embodiment of the cerebrospinal fluid cell morphology review process method described in this invention, in response to the selection operation of the distribution map function module, a full-slice image of the cerebrospinal fluid cells is displayed. The cerebrospinal fluid cell image is obtained by scanning a full-slice cerebrospinal fluid cell smear, and includes the following steps:

[0013] The prepared cerebrospinal fluid cell smear is placed on the scanner stage, and the scanner is started to scan the entire cerebrospinal fluid cell smear to obtain high-resolution digital image data and establish image index information. The user selects the distribution map function module through the operation interface, receives the selection operation command, and retrieves the corresponding cerebrospinal fluid cell whole-smear scan image according to the image index information.

[0014] In a preferred embodiment of the cerebrospinal fluid cell morphology review process method of the present invention, in response to the box selection and counting button for the cerebrospinal fluid cell image, a cell box selection interface is provided for the user to select the area to be counted, and the cerebrospinal fluid cell image is displayed on the cell box selection interface, including the following steps.

[0015] Upon detecting the user's click on the selection count button, the selection function module is activated. The system retrieves the currently displayed full-slice image data of cerebrospinal fluid cells from the memory cache, preparing it for use in the selection interface. Based on the retrieved image data, a cell selection interactive interface containing an image display area and an operation toolbar is generated. Pixel coordinates are established for the image display area, and the image pixel positions are mapped to interface coordinates. When the user performs a selection operation, the cerebrospinal fluid cell image is displayed on the cell selection interface.

[0016] As a preferred embodiment of the cerebrospinal fluid cell morphology review process method of the present invention, the method includes the following steps: in response to a user's selection operation, extracting nucleated cells present in the selected area and displaying the number of nucleated cells present in the selected area on the cell selection interface.

[0017] The system receives coordinate data generated by the user's bounding box operation, which is used to determine the precise boundary range of the target analysis area. Based on the acquired bounding box coordinates, it extracts image data blocks of the corresponding area from the full-slice cerebrospinal fluid cell image. The cropped area image is then denoised, enhanced, and standardized to optimize the image quality for subsequent cell identification. The system identifies all potential nucleated cell contours in the image and extracts morphological features from each detected cell contour to distinguish nucleated cells from other components. Finally, it filters out objects that meet the criteria for nucleated cells from all detected contours.

[0018] As a preferred embodiment of the cerebrospinal fluid cell morphology review process method of the present invention, the method includes the following steps: in response to the "confirm" button on the cell selection interface for the selection operation, marking and classifying all nucleated cells in the selected area, and counting the nucleated cells based on their type.

[0019] The system detects and responds to user clicks on the "OK" button on the cell selection interface, obtains confirmation instructions, verifies the completeness and validity of the received selection area coordinate data to ensure the accuracy of subsequent processing, extracts images of nucleated cells in the target area and performs feature enhancement processing, inputs the data into a pre-trained classification model through multi-dimensional feature extraction and standardization to obtain preliminary type determination, verifies the results after confidence evaluation, implements differentiated visual labeling for different cell types, and generates a classification count statistics table.

[0020] As a preferred embodiment of the cerebrospinal fluid cell morphology review process method of the present invention, in response to the selection operation of the cell image function module, images of all nucleated cells extracted within the selected area and their corresponding types are displayed for user review, including the following steps.

[0021] The review process is initiated by detecting the user's selection of the cell image function module, verifying the extracted nucleated cell image data and classification results, creating a dedicated review interface, intelligently arranging all nucleated cell images within the selected area, associating the classification label information corresponding to each cell image, activating various interactive functions, monitoring user operations in real time, and dynamically updating the review results.

[0022] As a preferred embodiment of the cerebrospinal fluid cell morphology review process method of the present invention, the output of a cerebrospinal fluid report based on the review results of the nucleated cells includes the following steps:

[0023] The system compiles nucleated cell classification data that has been manually reviewed and confirmed, standardizes the collected review results, converts the data format according to medical report standards, and automatically matches report templates based on the standardized data to generate cerebrospinal fluid reports.

[0024] In a second aspect, the present invention provides a cerebrospinal fluid cell morphology review process, apparatus, computer equipment and storage medium, including, said apparatus comprising a preview module, a first response module, a second response module, a third response module, a fourth response module and an output module;

[0025] The preview module is used to display the cerebrospinal fluid cell image in full in response to the selection operation of the distribution map function module; the cerebrospinal fluid cell image is an image obtained by scanning the entire cerebrospinal fluid cell smear.

[0026] The first response module is configured to respond to the box selection and counting button for the cerebrospinal fluid cell image, and provide a cell selection interface for the user to select the area to be counted; the cerebrospinal fluid cell image is displayed on the cell selection interface;

[0027] The second response module is used to respond to the user's selection operation, extract the nucleated cells present in the selected area, and display the number of nucleated cells present in the selected area on the cell selection interface;

[0028] The third response module is used to respond to the confirm button on the cell selection interface for the selection operation, mark and classify all nucleated cells in the selected area, and count the nucleated cells based on the type of the nucleated cells.

[0029] The fourth response module is used to respond to the selection operation of the cell map function module and display the images of all nucleated cells extracted in the selected area and their corresponding types for user review.

[0030] The output module is used to output a cerebrospinal fluid report based on the results of the review of the nucleated cells.

[0031] Thirdly, the present invention provides a computer device including a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, it implements any step of the cerebrospinal fluid cell morphology review process method as described in the first aspect of the present invention.

[0032] 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 morphology review process method as described in the first aspect of the present invention.

[0033] The beneficial effects of this invention are as follows: by automatically extracting, counting, labeling and classifying nucleated cells within the selected area on the cerebrospinal fluid cell image under the distribution map function module, the target number of nucleated cells in the cerebrospinal fluid can be quickly and accurately identified. In addition, this application also introduces a cell map function, which displays the image of the nucleated cells extracted within the selected area and their corresponding types for users to confirm and review, reducing the error rate and thus effectively improving the efficiency of the cerebrospinal fluid cell morphology review process. Attached Figure Description

[0034] 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.

[0035] Figure 1 This is an application scenario diagram of the cerebrospinal fluid cell morphology review process method provided in the embodiments of this application;

[0036] Figure 2 This is a flowchart of the cerebrospinal fluid cell morphology review process method provided in the embodiments of this application;

[0037] Figure 3 This is a schematic diagram of the distribution map functional module in the cerebrospinal fluid cell morphology review process method provided in this application;

[0038] Figure 4 This is a schematic diagram of the cell selection interface and selection counting button in the cerebrospinal fluid cell morphology review process method provided in this application;

[0039] Figure 5 This is a schematic diagram of the selected area in the cerebrospinal fluid cell morphology review process method provided in this application;

[0040] Figure 6 This is a schematic diagram illustrating the labeling of nucleated cells in the cerebrospinal fluid cell morphology review process method provided in this application;

[0041] Figure 7 A schematic diagram of the cell mapping functional module in the cerebrospinal fluid cell morphology review process method provided in this application;

[0042] Figure 8 A schematic diagram of the cerebrospinal fluid cell morphology review process device provided in the embodiments of this application;

[0043] Figure 9 A schematic diagram of the structure of a computer device provided in the embodiments of this application. Detailed Implementation

[0044] 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.

[0045] 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.

[0046] 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.

[0047] Example 1, referring to Figures 1-9 As one embodiment of the present invention, this embodiment provides a method for reviewing the morphology of cerebrospinal fluid cells, including the following steps:

[0048] S1. In response to the selection operation of the distribution map function module, the cerebrospinal fluid cell image is displayed in its entirety. The cerebrospinal fluid cell image is obtained by scanning the entire cerebrospinal fluid cell smear.

[0049] S1.1 Place the prepared cerebrospinal fluid cell smear on the scanner stage, start the scanner to scan the entire cerebrospinal fluid cell smear, acquire high-resolution digital image data, and establish image index information. The user selects the distribution map function module through the operation interface, receives the selection operation command, and retrieves the corresponding cerebrospinal fluid cell whole-smear scan image according to the image index information.

[0050] Furthermore, the prepared cerebrospinal fluid (CSF) cell smear is placed stably on the scanner stage, ensuring the smear surface is free of air bubbles and completely covers the scanning area. After the scanner is started, it performs a full scan of the CSF cell smear according to preset scanning parameters. During the scan, a high-precision optical lens acquires image data line by line, ultimately generating a high-resolution digital image of the entire CSF cell smear. After scanning, each CSF cell smear image is assigned a unique identifier and its storage path is recorded, establishing a complete image index. When the user selects the distribution map function module on the user interface, the interface receives the selection command and accurately retrieves the corresponding CSF cell smear image data from the storage location based on the pre-established image index information.

[0051] S2. In response to the box selection and counting button for the cerebrospinal fluid cell image, a cell selection interface is provided for the user to select the area to be counted, and the cerebrospinal fluid cell image is displayed on the cell selection interface.

[0052] S2.1 Detecting the user's operation command to click the selection count button, the selection function module is activated. The currently displayed cerebrospinal fluid cell whole-slice image data is retrieved from the memory cache and prepared for use in the selection interface display. Based on the retrieved image data, a cell selection interactive interface containing an image display area and an operation toolbar is generated. Pixel coordinates are established for the image display area, and the image pixel positions are mapped to interface coordinates. When the user performs a selection operation, the cerebrospinal fluid cell image is displayed on the cell selection interface.

[0053] Furthermore, upon detecting the user's click on the selection count button, the execution flow of the selection function module is immediately initiated. The currently displayed cerebrospinal fluid cell whole-slice image data is accurately retrieved from the memory cache, maintaining its original resolution and color information. Based on the retrieved cerebrospinal fluid cell whole-slice image data, an interactive interface with two main areas is generated: the image display area uses high-fidelity rendering technology to fully present the cerebrospinal fluid cell whole-slice image; the operation toolbar is located at the edge of the interface, providing functional controls such as a selection tool, magnifying glass, and count button. A precise pixel coordinate system is established for the image display area, and a bilinear interpolation algorithm maps each pixel position of the cerebrospinal fluid cell whole-slice image to interface coordinates, ensuring that the coordinate transformation process does not lose image accuracy. During the user's selection operation, the cerebrospinal fluid cell whole-slice image is always displayed in real-time within the image display area of ​​the cell selection interface, maintaining image display stability.

[0054] S3. In response to the user's selection operation, extract the nucleated cells present in the selected area and display the number of nucleated cells present in the selected area on the cell selection interface, including the following steps.

[0055] S3.1 Receive coordinate data generated by the user's bounding box operation, which is used to determine the precise boundary range of the target analysis area. Based on the obtained bounding box coordinates, extract the corresponding image data blocks from the whole cerebrospinal fluid cell image. Perform denoising, enhancement, and standardization processing on the cropped area image to optimize the image quality of subsequent cell recognition. Identify all potential nucleated cell contours in the image. Extract morphological features from each detected cell contour to distinguish nucleated cells from other components. Filter out objects that meet the nucleated cell criteria from all detected contours.

[0056] Furthermore, after receiving the coordinate data generated by the user's bounding box operation, the validity of the coordinate data is first verified to ensure that it is within the valid range of the whole cerebrospinal fluid cell image. Based on the verified bounding box coordinates, a bilinear interpolation algorithm is used to accurately extract the corresponding image data blocks from the whole cerebrospinal fluid cell image, maintaining the resolution and color depth of the original image. Gaussian filtering for noise reduction, histogram equalization enhancement, and grayscale normalization are sequentially performed on the cropped region image data blocks to optimize the image quality to a state suitable for cell recognition. The Canny edge detection algorithm is used to identify all potential nucleated cell contours in the preprocessed image, and morphological feature parameters, including area, perimeter, roundness, and grayscale distribution, are calculated for each detected cell contour. According to the preset nucleated cell feature threshold range, objects with an area greater than 50 pixels and a roundness greater than 0.7 are selected from all detected contours and determined to be valid nucleated cells.

[0057] S4. In response to the confirmation button for the selection operation on the cell selection interface, mark and classify all nucleated cells in the selected area, and count the nucleated cells based on their type.

[0058] S4.1 Detects and responds to the user's click on the "OK" button on the cell selection interface, obtains the confirmation instruction, verifies whether the received selection area coordinate data is complete and valid, ensures the accuracy of subsequent processing, extracts the nucleated cell image of the target area and performs feature enhancement processing, inputs it into the pre-trained classification model through multi-dimensional feature extraction and standardization to obtain a preliminary type determination, verifies the results after confidence evaluation, implements differentiated visual labeling for different types of cells, and generates a classification count statistics table.

[0059] Furthermore, after detecting and responding to the user's click on the "OK" button on the cell selection interface, a confirmation instruction is immediately obtained, verifying whether the received selection area coordinate data meets the minimum area requirement (100 pixels in the example) and shape validity. After confirming the data is complete and valid, nucleated cell image data blocks of the target region are extracted from the full-slice cerebrospinal fluid cell image. Image denoising is performed using a combination of Gaussian filtering and median filtering, followed by feature enhancement processing through histogram equalization. Multidimensional feature vectors, including morphological features (area, perimeter, roundness), texture features (gray-level co-occurrence matrix energy, contrast), and staining features (RGB channel distribution), are extracted from the preprocessed nucleated cell images. The extracted raw features are then Z-score standardized to eliminate dimensional differences. The standardized feature vectors are input into a pre-trained cerebrospinal fluid cell classification model to obtain preliminary type determination results for each cell (e.g., lymphocytes, neutrophils, etc.). The confidence level of the classification results is evaluated, and cases with confidence levels lower than the example value of 0.85 are selected for manual verification. Based on the finally confirmed cell type, differential visualization labels are implemented on the original image using different colors (in the example, lymphocytes are labeled in blue and neutrophils are labeled in green) and symbols, while generating a classification count statistics table containing the number and percentage statistics of each type of cell.

[0060] S5. In response to the selection operation of the cell image function module, the images of all nucleated cells extracted within the selected area and their corresponding types will be displayed for user review.

[0061] S5.1. The review process is initiated by detecting the user's selection of the cell image function module, verifying the extracted nucleated cell image data and classification results, creating a dedicated review interface, intelligently arranging all nucleated cell images within the selected area, associating the classification label information corresponding to each cell image, activating various interactive functions, monitoring user operations in real time, and dynamically updating the review results.

[0062] Furthermore, upon detecting a user's selection of the cell image module, the review process is immediately initiated. First, the integrity and consistency of the extracted nucleated cell image data and classification results are verified, ensuring the image data is undamaged and the classification labels are fully corresponding. After successful verification, a dedicated review interface is created, divided into three functional areas: an image display area, a classification information area, and an operation control area. All nucleated cell images within the selected area are intelligently arranged according to cell type and spatial distribution characteristics, using a grid-based arrangement with cells of the same type arranged adjacently, and each cell image occupying a fixed-size display unit (100×100 pixels in the example). During the layout process, each cell image is strictly associated with its corresponding classification label information, ensuring a synchronous correspondence between display position and label information. The review interface activates interactive functions including classification correction, image zoom, and comparison viewing, supporting user review through clicks, drags, and other operations. All user actions on the review interface are monitored and recorded in real time, including classification modifications and note additions, and the review result database is dynamically updated based on user actions, ensuring real-time synchronization of the review status.

[0063] S6. Output a cerebrospinal fluid report based on the results of the review of the nucleated cells.

[0064] S6.1 Summarize the nucleated cell classification data that has been manually reviewed and confirmed, standardize the collected review results, convert the data format according to medical report specifications, and automatically match the report template based on the standardized data to generate a cerebrospinal fluid report.

[0065] Furthermore, after aggregating the nucleated cell classification data that has been manually reviewed and confirmed, the data integrity is first verified to ensure that all necessary fields, such as lymphocyte count and neutrophil count, are included. The collected review results are then standardized, converting the raw data into a standardized format that conforms to the third edition of the "Clinical Laboratory Report Writing Standards," including standardized units of measurement and terminology. Based on the standardized nucleated cell classification data, the most suitable template is automatically matched from a pre-set cerebrospinal fluid (CSF) test report template library. Matching criteria include the number of test items and specific clinical department requirements. Using the successfully matched template, the standardized nucleated cell classification data is filled into the corresponding fields, derived indicators are automatically calculated, and a complete CSF report document containing text descriptions, data tables, and key indicator curves is generated. The final output format adopts the PDF / A-1 standard to ensure long-term readability.

[0066] This embodiment also provides a cerebrospinal fluid cell morphology review process, device, computer equipment, and storage medium, including: the device includes a preview module, a first response module, a second response module, a third response module, a fourth response module, and an output module;

[0067] The preview module is used to display the cerebrospinal fluid cell image in full in response to the selection operation of the distribution map function module; the cerebrospinal fluid cell image is an image obtained by scanning the entire cerebrospinal fluid cell smear.

[0068] The first response module is configured to respond to the box selection and counting button for the cerebrospinal fluid cell image, and provide a cell selection interface for the user to select the area to be counted; the cerebrospinal fluid cell image is displayed on the cell selection interface;

[0069] The second response module is used to respond to the user's selection operation, extract the nucleated cells present in the selected area, and display the number of nucleated cells present in the selected area on the cell selection interface;

[0070] The third response module is used to respond to the confirm button on the cell selection interface for the selection operation, mark and classify all nucleated cells in the selected area, and count the nucleated cells based on the type of the nucleated cells.

[0071] The fourth response module is used to respond to the selection operation of the cell map function module and display the images of all nucleated cells extracted in the selected area and their corresponding types for user review.

[0072] The output module is used to output a cerebrospinal fluid report based on the results of the review of the nucleated cells.

[0073] This embodiment also provides a computer device applicable to the cerebrospinal fluid cell morphology review process 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 morphology review process method proposed in the above embodiment.

[0074] 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.

[0075] This embodiment also provides a storage medium storing a computer program that, when executed by a processor, implements the method for implementing the cerebrospinal fluid cell morphology review process 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.

[0076] In summary, this invention, through the automatic extraction, counting, labeling, and classification of nucleated cells within a selected area on a cerebrospinal fluid cell image using the distribution map function module, can quickly and accurately identify the target number of nucleated cerebrospinal fluid cells. In addition, this application also introduces a cell map function, which displays the images of the nucleated cells extracted within the selected area and their corresponding types for user confirmation and verification, reducing the error rate and thus effectively improving the efficiency of the cerebrospinal fluid cell morphology review process.

[0077] Example 2, refer to Figures 1 to 9 This is the second embodiment of the present invention, which provides a method for reviewing the morphology of cerebrospinal fluid cells, including the following steps.

[0078] Figure 1 This diagram illustrates an application scenario for a cerebrospinal fluid cell morphology review process method provided in one embodiment of this application. Figure 1 As shown, both the cerebrospinal fluid (CSF) review device 101 and the scanner 102 can transmit data via a network. The scanner 102 is used to scan CSF cell smears to obtain CSF cell images and transmit these images to the CSF review device 101. After acquiring cerebrospinal fluid (CSF) cell images, the CSF review device 101 displays the entire CSF cell image in response to the selection operation of the distribution map function module. The CSF cell image is obtained by scanning the entire CSF cell smear. The CSF review device 101 also provides a cell selection interface for users to select the area to be counted in response to the box selection and counting button for the CSF cell image. The CSF cell image is displayed on the cell selection interface. In response to the user's box selection operation, nucleated cells in the selected area are extracted, and the number of nucleated cells in the selected area is displayed on the cell selection interface. In response to the confirmation button for the box selection operation on the cell selection interface, all nucleated cells in the selected area are marked and classified, and the nucleated cells are counted based on their type. In response to the selection operation of the cell map function module, the images of all nucleated cells extracted in the selected area and their corresponding types are displayed for user review. Finally, the CSF review device 101 outputs a CSF report based on the results of the review of the nucleated cells.

[0079] This application provides a method for reviewing the morphology of cerebrospinal fluid cells, such as... Figure 2 As shown, the method includes the following steps:

[0080] Step S210: In response to the selection operation of the distribution map function module, the cerebrospinal fluid cell image is displayed in its entirety; the cerebrospinal fluid cell image is an image obtained by scanning the entire cerebrospinal fluid cell smear.

[0081] Figure 3 This is a schematic diagram of the distribution map functional module in the cerebrospinal fluid cell morphology review process method provided in this application, as shown below. Figure 3 As shown, when the user selects the distribution map function module, in response to the selection operation, the server will display the entire cerebrospinal fluid cell image, allowing the user to select the region of interest.

[0082] In step S220, in response to the box selection and counting button for the cerebrospinal fluid cell image, a cell selection interface is provided for the user to select the area to be counted; the cerebrospinal fluid cell image is displayed on the cell selection interface.

[0083] Figure 4The diagram illustrates the cell selection interface and selection counting button in the cerebrospinal fluid cell morphology review process method provided in this application, as shown below. Figure 4 As shown, when a user wants to detect a target number of nucleated cells in cerebrospinal fluid, the user can click the box selection and counting button. In response to the box selection and counting button for the cerebrospinal fluid cell image, a cell selection interface is provided for the user to select the area that needs to be counted.

[0084] In step S230, in response to the user's selection operation, the nucleated cells in the selected area are extracted, and the number of nucleated cells in the selected area is displayed on the cell selection interface.

[0085] Figure 5 This is a schematic diagram of the selected area in the cerebrospinal fluid cell morphology review process method provided in this application, such as... Figure 5 As shown, when the user makes a selection, the system responds to the user's selection operation by extracting the nucleated cells in the selected area and displays the number of nucleated cells in the selected area on the cell selection interface. The user can determine whether the number of nucleated cells meets the requirements based on the displayed number of nucleated cells.

[0086] In step S240, in response to the confirmation button for the selection operation on the cell selection interface, all nucleated cells in the selected area are marked and classified, and the nucleated cells are counted based on their type.

[0087] like Figure 5 As shown, when the user confirms that the number of nucleated cells in the selected area meets the requirements, the user can click the confirmation button on the cell selection interface. In response to the confirmation button for the selection operation on the cell selection interface, all nucleated cells in the selected area are marked and classified, and the nucleated cells are counted based on their type. Figure 6 This is a schematic diagram illustrating the labeling of nucleated cells according to the cerebrospinal fluid cell morphology review process method provided in this application, such as... Figure 6 As shown, by marking all nucleated cells in the selected area, rapid localization of nucleated cells in the selected area can be achieved.

[0088] In step S250, in response to the selection operation of the cell map function module, the images of all nucleated cells extracted within the selected area and their corresponding types will be displayed for user review.

[0089] Figure 7 This is a schematic diagram of the cell mapping functional module in the cerebrospinal fluid cell morphology review process method provided in this application, as shown below. Figure 7As shown, when the user selects the cell map function module, in response to the selection operation of the cell map function module, the images of all nucleated cells extracted within the selected area and their corresponding types will be displayed for the user to review. If the user reviews that the type of nucleated cells is incorrect, it can be corrected in time.

[0090] Step S260: Output a cerebrospinal fluid report based on the results of reviewing nucleated cells.

[0091] In existing technologies, cerebrospinal fluid (CSF) cell smears are placed on a microscope platform. Doctors use low magnification to observe the entire smear, identifying areas where CSF nucleated cells need to be counted. After locating these areas, high magnification is used to observe, classify, and count the target number of CSF nucleated cells based on their type. The results are recorded and a CSF report is generated. However, manual review of CSF cell images is time-consuming, prone to omissions, and involves prolonged work under a microscope, increasing the risk of fatigue and misjudgment. These factors contribute to the low efficiency of existing CSF cell morphology review processes.

[0092] To address the aforementioned issues, this application proposes a method for reviewing cerebrospinal fluid (CSF) cell morphology. This method involves displaying a full-slice CSF cell image in response to a selection operation in the distribution map function. The CSF cell image is obtained by scanning a full-slice CSF cell smear. In response to a selection and counting button on the CSF cell image, a cell selection interface is provided for the user to select the area to be counted. The CSF cell image is displayed on the cell selection interface. In response to the user's selection operation, nucleated cells within the selected area are extracted, and the number of nucleated cells in the selected area is displayed on the cell selection interface. In response to a confirmation button on the cell selection interface, all nucleated cells within the selected area are marked and classified, and counted based on their type. In response to a selection operation in the cell map function, images of all extracted nucleated cells within the selected area and their corresponding types are displayed for user review.

[0093] Figure 8 This is a schematic diagram of a cerebrospinal fluid cell morphology review process device according to an embodiment of the present invention, such as... Figure 8 As shown, a cerebrospinal fluid cell morphology review process device 30 is provided. The device includes a preview module 31, a first response module 32, a second response module 33, a third response module 34, a fourth response module 35, and an output module 36.

[0094] The preview module 31 is used to display the cerebrospinal fluid cell image in full in response to the selection operation of the distribution map function module; the cerebrospinal fluid cell image is the image obtained by scanning the cerebrospinal fluid cell smear in full.

[0095] The first response module 32 is used to respond to the box selection and counting button for the cerebrospinal fluid cell image, and provides a cell selection interface for the user to select the area that needs to be counted; the cerebrospinal fluid cell image is displayed on the cell selection interface;

[0096] The second response module 33 is used to respond to the user's selection operation, extract the nucleated cells in the selected area, and display the number of nucleated cells in the selected area on the cell selection interface.

[0097] The third response module 34 is used to respond to the confirm button for the selection operation on the cell selection interface, mark and classify all nucleated cells in the selected area, and count the nucleated cells based on the type of nucleated cells.

[0098] The fourth response module 35 is used to respond to the selection operation of the cell map function module, and will display the images of all nucleated cells extracted within the selected area and their corresponding types for user review;

[0099] Output module 36 is used to output a cerebrospinal fluid report based on the results of the review of nucleated cells.

[0100] The aforementioned cerebrospinal fluid (CSF) cell morphology review process device 30 displays a full-slice CSF cell image in response to a selection operation of the distribution map function. The CSF cell image is obtained by scanning a full-slice CSF cell smear. In response to a selection and counting button on the CSF cell image, a cell selection interface is provided for the user to select the area to be counted. The CSF cell image is displayed on the cell selection interface. In response to the user's selection operation, nucleated cells in the selected area are extracted, and the number of nucleated cells in the selected area is displayed on the cell selection interface. In response to a confirmation button on the cell selection interface, all nucleated cells in the selected area are marked and classified, and the nucleated cells are counted based on their type. In response to a selection operation of the cell map function, images of all extracted nucleated cells and their corresponding types are displayed for user review. A CSF report is output based on the review results of the nucleated cells. This application automatically extracts, counts, labels, and classifies nucleated cells within a selected area on a cerebrospinal fluid cell image using the distribution map function module. This allows for the rapid and accurate identification of a target number of nucleated cerebrospinal fluid cells. Furthermore, this application introduces a cell map function, which displays images of the extracted nucleated cells within the selected area along with their corresponding types for user confirmation and review, reducing the error rate and effectively improving the efficiency of the cerebrospinal fluid cell morphology review process.

[0101] It should be noted that the above modules can be functional modules or program modules, and can be implemented in software or hardware. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or they can be stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0102] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 9 As shown. The computer device includes a processor, memory, network interface, and database 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, computer programs, and database. The memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores a set of preset configuration information. The network interface communicates with external terminals via a network connection. When the computer program is executed by the processor, it implements the aforementioned cerebrospinal fluid cell morphology review process method.

[0103] In one embodiment, a computer device is provided, which may be a terminal. The computer device includes a processor, memory, a network interface, a display screen, and an input device connected via a system bus. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, it implements a method for reviewing cerebrospinal fluid cell morphology. The display screen of the computer device may be a liquid crystal display (LCD) or an e-ink display. The input device of the computer device may be a touch layer covering the display screen, or buttons, a trackball, or a touchpad located on the casing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0104] Those skilled in the art will understand that Figure 9 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0105] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0106] In response to the selection operation of the distribution map function module, the cerebrospinal fluid cell image is displayed in its entirety; the cerebrospinal fluid cell image is obtained by scanning the entire cerebrospinal fluid cell smear.

[0107] In response to the selection and counting button for cerebrospinal fluid cell images, a cell selection interface is provided for users to select the area that needs to be counted; the cerebrospinal fluid cell image is displayed on the cell selection interface;

[0108] In response to the user's selection operation, the nucleated cells in the selected area are extracted, and the number of nucleated cells in the selected area is displayed on the cell selection interface;

[0109] In response to the "OK" button on the cell selection interface, all nucleated cells in the selected area are marked and classified, and the number of nucleated cells is counted based on their type.

[0110] In response to the selection operation of the cell map function module, the images of all nucleated cells extracted within the selected area and their corresponding types will be displayed for user review;

[0111] A cerebrospinal fluid report is generated based on the results of the review of nucleated cells.

[0112] 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 reviewing the morphology of cerebrospinal fluid cells, characterized by: This includes displaying a full-slice cerebrospinal fluid cell image in response to the selection operation of the distribution map function module. The cerebrospinal fluid cell image is obtained by scanning a full-slice cerebrospinal fluid cell smear. In response to the box selection and counting button for the cerebrospinal fluid cell image, a cell selection interface is provided for the user to select the area to be counted, and the cerebrospinal fluid cell image is displayed on the cell selection interface; In response to the user's selection operation, the nucleated cells present in the selected area are extracted, and the number of nucleated cells present in the selected area is displayed on the cell selection interface; In response to the confirmation button for the selection operation on the cell selection interface, all nucleated cells in the selected area are marked and classified, and the nucleated cells are counted based on their type. In response to the selection operation of the cell map function module, the images of all nucleated cells extracted within the selected area and their corresponding types will be displayed for user review. A cerebrospinal fluid report is generated based on the results of the review of the nucleated cells.

2. The cerebrospinal fluid cell morphology review process method as described in claim 1, characterized in that: In response to the selection operation of the distribution map function module, the cerebrospinal fluid cell image is displayed in its entirety. The cerebrospinal fluid cell image is obtained by scanning a full-slice of a cerebrospinal fluid cell smear, and includes the following steps: The prepared cerebrospinal fluid cell smear is placed on the scanner stage, and the scanner is started to scan the entire cerebrospinal fluid cell smear to obtain high-resolution digital image data and establish image index information. The user selects the distribution map function module through the operation interface, receives the selection operation command, and retrieves the corresponding cerebrospinal fluid cell whole-smear scan image according to the image index information.

3. The cerebrospinal fluid cell morphology review process method as described in claim 2, characterized in that: In response to the selection and counting button for the cerebrospinal fluid cell image, a cell selection interface is provided for the user to select the area to be counted. The cerebrospinal fluid cell image is displayed on the cell selection interface, including the following steps. Upon detecting the user's click on the selection count button, the selection function module is activated. The system retrieves the currently displayed full-slice image data of cerebrospinal fluid cells from the memory cache, preparing it for use in the selection interface. Based on the retrieved image data, a cell selection interactive interface containing an image display area and an operation toolbar is generated. Pixel coordinates are established for the image display area, and the image pixel positions are mapped to interface coordinates. When the user performs a selection operation, the cerebrospinal fluid cell image is displayed on the cell selection interface.

4. The cerebrospinal fluid cell morphology review process method as described in claim 3, characterized in that: In response to a user's selection action, nucleated cells within the selected area are extracted, and the number of nucleated cells within the selected area is displayed on the cell selection interface. This includes the following steps: The system receives coordinate data generated by the user's bounding box operation, which is used to determine the precise boundary range of the target analysis area. Based on the acquired bounding box coordinates, it extracts image data blocks of the corresponding area from the full-slice cerebrospinal fluid cell image. The cropped area image is then denoised, enhanced, and standardized to optimize the image quality for subsequent cell identification. The system identifies all potential nucleated cell contours in the image and extracts morphological features from each detected cell contour to distinguish nucleated cells from other components. Finally, it filters out objects that meet the criteria for nucleated cells from all detected contours.

5. The cerebrospinal fluid cell morphology review process method as described in claim 4, characterized in that: In response to the "OK" button on the cell selection interface for the selection operation, all nucleated cells in the selected area are marked and classified, and the nucleated cells are counted based on their type. Includes the following steps, The system detects and responds to user clicks on the "OK" button on the cell selection interface, obtains confirmation instructions, verifies the completeness and validity of the received selection area coordinate data to ensure the accuracy of subsequent processing, extracts images of nucleated cells in the target area and performs feature enhancement processing, inputs the data into a pre-trained classification model through multi-dimensional feature extraction and standardization to obtain preliminary type determination, verifies the results after confidence evaluation, implements differentiated visual labeling for different cell types, and generates a classification count statistics table.

6. The cerebrospinal fluid cell morphology review process method as described in claim 5, characterized in that: In response to the selection operation of the cell image function module, images of all nucleated cells extracted within the selected area and their corresponding types are displayed for user review, including the following steps: The review process is initiated by detecting the user's selection of the cell image function module, verifying the extracted nucleated cell image data and classification results, creating a dedicated review interface, intelligently arranging all nucleated cell images within the selected area, associating the classification label information corresponding to each cell image, activating various interactive functions, monitoring user operations in real time, and dynamically updating the review results.

7. The cerebrospinal fluid cell morphology review process method as described in claim 6, characterized in that: The process of generating a cerebrospinal fluid report based on the results of the review of the nucleated cells includes the following steps. The system compiles nucleated cell classification data that has been manually reviewed and confirmed, standardizes the collected review results, converts the data format according to medical report standards, and automatically matches report templates based on the standardized data to generate cerebrospinal fluid reports.

8. A cerebrospinal fluid cell morphology review process, apparatus, computer equipment, and storage medium, based on the cerebrospinal fluid cell morphology review process method according to any one of claims 1 to 7, characterized in that: The device includes a preview module, a first response module, a second response module, a third response module, a fourth response module, and an output module. The preview module is used to display the cerebrospinal fluid cell image in full in response to the selection operation of the distribution map function module; the cerebrospinal fluid cell image is an image obtained by scanning the entire cerebrospinal fluid cell smear. The first response module is configured to respond to the box selection and counting button for the cerebrospinal fluid cell image, and provide a cell selection interface for the user to select the area to be counted; the cerebrospinal fluid cell image is displayed on the cell selection interface; The second response module is used to respond to the user's selection operation, extract the nucleated cells present in the selected area, and display the number of nucleated cells present in the selected area on the cell selection interface; The third response module is used to respond to the confirm button on the cell selection interface for the selection operation, mark and classify all nucleated cells in the selected area, and count the nucleated cells based on the type of the nucleated cells. The fourth response module is used to respond to the selection operation of the cell map function module and display the images of all nucleated cells extracted in the selected area and their corresponding types for user review. The output module is used to output a cerebrospinal fluid report based on the results of the review of the nucleated cells.

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 morphology review process 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 morphology review process method according to any one of claims 1 to 7.

Images