Cell smear auditing method and device, computer equipment and storage medium

Abstract

The invention discloses a cell smear auditing method and device, computer equipment and a storage medium, and relates to medical image analys.The method comprises the steps that specific cell types needing to be concerned for a cell smear are preset; acquiring a cell image obtained by performing full scanning on the cell smear, and detecting the cell image by using an image detection algorithm; and when specific cells of a preset type are detected in the cell image, intercepting the detected specific cells from the cell image, and counting the detected specific cells based on the types of the detected specific cells. According to the method, the cell image corresponding to the cell smear is detected and automatically recognized, so that the integrity and accuracy of data are improved, and the auditing efficiency of the cell smear is improved. And by recording the position information of the detected specific cells in the cell image, the positions of the specific cells can be marked, so that the reliability of cell smear auditing is ensured.

Description

Technical Field

[0001] This invention relates to medical image analysis, and in particular to methods, apparatus, computer equipment, and storage media for reviewing cell smears. Background Technology

[0002] Cell smears are widely used in disease diagnosis. Doctors diagnose the type and severity of a disease by examining the types and quantities of cells present in the smear. Because the composition of cells in a smear varies depending on the type of disease, the review process often requires attention to the specific types of cells and their quantities.

[0003] In existing technologies, the review of cell smears involves manual observation to identify specific cell types of interest, followed by manual counting when such types are observed. However, cerebrospinal fluid cells are few in number and vary in morphology. Furthermore, the special centrifugation process required for slide collection easily leads to overlapping and omissions during manual observation, affecting the completeness and accuracy of the data. Additionally, when secondary verification of specific cell types is needed, relocation is time-consuming, hindering rapid and accurate verification and impacting data reliability. Moreover, manual observation and counting are slow, significantly reducing review efficiency. 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 cell smears to solve the problems of insufficient integrity, accuracy, and reliability, as well as low review efficiency, in reviewing cell smears.

[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 reviewing cell smears, which includes pre-setting specific cell types that need to be considered for the cell smears;

[0008] A cell image is obtained by scanning the entire cell smear, and the cell image is detected using an image detection algorithm;

[0009] When a specific cell of a preset type is detected in the cell image, the detected specific cell is cropped from the cell image and counted based on the type of the detected specific cell, and the location information of the detected specific cell in the cell image is recorded.

[0010] When the cell image is opened, the detected specific cells are labeled based on the location information.

[0011] As a preferred embodiment of the cell smear review method of the present invention, in response to the click operation of the cell type preset button for the cell smear, a cell type preset interface is provided, a list of all cell types is displayed in the cell type preset interface, and a check box is displayed after each cell type for the user to select.

[0012] In response to the click of the "OK" button on the preset cell type interface, the selected cell type becomes the specific cell type that needs to be focused on for the cell smear.

[0013] As a preferred embodiment of the cell smear review method of the present invention, the method includes the following steps: Pre-setting specific cell types to be considered for the cell smear.

[0014] The user clicks the preset button to activate the cell type selection interface. The system responds to the operation and loads the preset function module. The preset interface fully displays a list of all available cell types. Each option is equipped with an interactive checkbox control. The user specifies the specific cell types to focus on by checking the boxes, forming a preliminary selection set. The user clicks the OK button to complete the selection. The confirmed cell type set is captured and set as the core parameter of the current review task, and then passed to the detection algorithm module.

[0015] As a preferred embodiment of the cell smear review method of the present invention, the method includes the following steps: acquiring a cell image obtained by scanning the entire cell smear, and detecting the cell image using an image detection algorithm.

[0016] The scanning device is activated and the parameters are calibrated to prepare for a full-slide scan of the cell smear. The high-precision scanner performs the full-slide scan, converting the physical smear into a high-resolution digital image. The original scanned image is subjected to noise reduction, contrast adjustment, and standardization to improve image quality. The corresponding image recognition algorithm and parameter configuration are automatically loaded according to the preset cell type. Multi-dimensional feature extraction is performed on the optimized image to identify potential cell morphological features and locate specific cells in the image that meet the preset conditions.

[0017] In a preferred embodiment of the cell smear review method of the present invention, when a preset type of specific cell is detected in the cell image, the detected specific cell is cropped from the cell image and the detected specific cell is counted based on its type, including the following steps:

[0018] The system receives the preliminary identification results of the preset type-specific cells output by the image detection algorithm, performs secondary verification on the preliminary detection results, eliminates false detection targets, confirms the real specific cells, accurately extracts the image region containing specific cells from the original cell image, extracts key identification parameters such as morphological features and texture features from the extracted cell image, compares the extracted features with the preset cell type feature library, confirms the specific type of each detected cell, and counts the number of specific cells of each type.

[0019] As a preferred embodiment of the cell smear review method of the present invention, the method includes the following steps: recording the location information of detected specific cells in the cell image.

[0020] A standardized coordinate system is established based on the full-scan image. Edge detection and contour extraction are performed on the identified specific cells to obtain the precise boundary information of the cells in the image. Based on the extracted cell contours, the coordinates of the geometric center point of each specific cell are obtained. Using the center point as a reference, the coordinates of the bounding box of the outer rectangle are generated, and the absolute coordinates are converted into standardized relative position parameters relative to the full-scan image.

[0021] In a preferred embodiment of the cell smear review method of the present invention, when the cell image is opened, the detected specific cells are marked based on the location information, including the following steps:

[0022] The system acquires the recorded metadata of specific cell location information, sets visualization parameters such as marker symbols, colors, and sizes according to the user's preset marker style requirements, accurately matches and calibrates the stored location coordinates with the currently displayed image coordinate system, generates corresponding marker graphic elements based on the location information and style parameters, and automatically adjusts the level of detail of the marker elements according to the image display level before marking.

[0023] In a second aspect, the present invention provides a cell smear review device, computer equipment and storage medium, including the preset module, which is used to preset the specific cell types that need to be focused on for the cell smear;

[0024] The acquisition module is used to acquire cell images obtained by scanning the entire cell smear, and to detect the cell images using an image detection algorithm;

[0025] The recording module is used to extract the detected specific cells from the cell image and count the detected specific cells based on their type when a specific cell of a preset type is detected in the cell image, and to record the location information of the detected specific cells in the cell image.

[0026] The labeling module is used to label the detected specific cells based on the location information when the cell image is opened.

[0027] 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 cell smear review method as described in the first aspect of the present invention.

[0028] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements any step of the cell smear review method as described in the first aspect of the present invention.

[0029] The beneficial effects of this invention are as follows: By utilizing image detection algorithms to detect cell images corresponding to cell smears, specific cell types requiring attention are automatically identified and counted, reducing omissions, effectively improving data integrity and accuracy, and increasing the efficiency of cell smear review. Furthermore, by recording the location information of detected specific cells in the cell image, this application can mark the locations of specific cell types, effectively improving review efficiency and ensuring the reliability of cell smear review. Attached Figure Description

[0030] 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.

[0031] Figure 1 This is an application scenario diagram of the cell smear review method provided in the embodiments of this application;

[0032] Figure 2 This is a flowchart of a cell smear review method provided according to an embodiment of this application;

[0033] Figure 3 This is a schematic diagram of the cell type preset interface in the cell smear review method provided in the embodiments of this application;

[0034] Figure 4 This is a schematic diagram illustrating cell labeling in the cell smear review method provided in this application;

[0035] Figure 5 This is a schematic diagram of the structure of the cell smear review device provided in the embodiments of this application;

[0036] Figure 6This is a schematic diagram of the structure of a computer device provided according to an embodiment of this application. Detailed Implementation

[0037] 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.

[0038] 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.

[0039] Secondly, the term "one embodiment" or "example" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the invention. The appearance of an embodiment in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that mutually excludes other embodiments.

[0040] Example 1, referring to Figures 1-6 This is the first embodiment of the present invention, which provides a method for reviewing cell smears, including the following steps:

[0041] S1. In response to the click operation of the cell type preset button for the cell smear, a cell type preset interface is provided, in which a list of all cell types is displayed, and a check box is displayed after each cell type for the user to select.

[0042] Furthermore, when a click on the preset cell type button for a cell smear is detected, the interface display logic is immediately activated. A predefined interface layout template and cell type data resources are retrieved, and the preset cell type interface is fully loaded according to the preset style specifications. The main area of ​​the interface is set as a scrollable list container, which displays all cell type options in a vertical arrangement. Complete cell type list data is obtained from the cell type database, including but not limited to: squamous epithelial cells, columnar epithelial cells, neutrophils, lymphocytes, macrophages, abnormal cells, and other medical standard classifications. Each cell type entry is formatted according to a unified standard, including standardized cell type name text and functional controls.

[0043] It should be noted that a standardized checkbox control is added to a fixed position to the right of each cell type name text. The checkbox adopts a square design, and its default state is unselected. It supports mouse clicks and touch operations to toggle the selection state. The visual feedback of the checkbox includes: an empty square when unselected, and a solid square with a checkmark icon when selected. An OK button is placed in a fixed position at the bottom of the interface, ready to receive the user's confirmation instruction after completing the selection. The OK button maintains a standard size and eye-catching color scheme, and automatically becomes clickable after the user completes the selection of any cell type.

[0044] S1.1 In response to the click operation of the "OK" button on the preset cell type interface, the selected cell type becomes the specific cell type that needs to be focused on for the cell smear.

[0045] Furthermore, when the "OK" button on the cell type preset interface is clicked, the preset confirmation process is immediately triggered, the final processing of the cell type selection results is initiated, the selection status of all cell type options in the cell type preset interface is checked, the names of the selected cell types are collected, the unselected items are excluded, and the list of selected cell type names is converted into a standardized data format, such as organizing the selected squamous epithelial cells and lymphocytes into an ordered dataset.

[0046] S2. Preset the specific cell types that need to be considered for the cell smear.

[0047] S2.1 When the user clicks the preset button to activate the cell type selection interface, the system responds to the operation and loads the preset function module. The preset interface fully displays a list of all available cell types. Each option is equipped with an interactive checkbox control. The user specifies the specific cell types to focus on by checking the boxes, forming a preliminary selection set. The user clicks the OK button to complete the selection, captures the confirmed cell type set, sets the confirmed cell type set as the core parameter of the current review task, and passes it to the detection algorithm module.

[0048] Furthermore, upon detecting a click on the preset cell type button, the cell type selection interface is immediately activated. This interface loads fully according to the preset layout specifications, and the display area is set as a scrollable list container. The cell type selection interface vertically displays all available cell type options (including but not limited to standard classifications such as squamous epithelial cells, columnar epithelial cells, neutrophils, and lymphocytes). Each cell type entry includes standardized name text and an interactive checkbox control in a fixed position on the right. Users interact with the checkbox control by clicking. The checkbox defaults to a hollow square and switches to a solid state with a checkmark icon after clicking, completing the specification of the specific cell type of interest. Each click updates the selection status in real time, forming a dynamically changing initial selection set. For example, a user can sequentially select target types such as neutrophils and abnormal cells. When the user clicks the "OK" button at the bottom of the interface, all currently selected cell types are immediately captured, generating a confirmed cell type set. After being standardized and converted, this dataset is specifically bound to the current cell smear sample. Simultaneously, it automatically adjusts the detection parameters and feature matching thresholds of subsequent image analysis algorithms. The confirmed cell type set is then passed as core parameters to the detection algorithm module, maintaining data integrity and consistency throughout the parameter transfer process. These preset parameters directly guide the execution strategy of subsequent full-smear scanning and automated detection procedures, ensuring the analysis process is targeted.

[0049] S3. Obtain the cell image obtained by scanning the entire cell smear, and use an image detection algorithm to detect the cell image.

[0050] S3.1 Activate the scanning device and calibrate the parameters to prepare for a full-slide scan of the cell smear. The high-precision scanner performs a full-slide scan, converting the physical smear into a high-resolution digital image. The original scanned image is subjected to noise reduction, contrast adjustment, and standardization to improve image quality. The corresponding image recognition algorithm and parameter configuration are automatically loaded according to the preset cell type. Multi-dimensional feature extraction is performed on the optimized image to identify potential cell morphological features and locate specific cells in the image that meet the preset conditions.

[0051] Furthermore, the high-precision scanner automatically executes an initial calibration procedure upon startup, adjusting the optical lens focal length, illumination intensity, and color balance parameters to ensure the device is in optimal working condition. The calibration process includes white balance correction, resolution testing, and color space verification, providing a precise hardware foundation for cell smear scanning. The scanner performs a full scan of the cell smear according to a preset scanning path and resolution parameters (e.g., using a 40x objective lens and 0.25μm / pixel resolution). During scanning, a line-by-line push-scan method is used, capturing optical signals through a high-sensitivity CCD sensor to convert the physical smear into a 24-bit true-color digital image. The raw image data is temporarily stored in a lossless format, and the acquired raw scan image undergoes multi-step processing: first, an adaptive noise reduction algorithm is applied to eliminate optical noise; then, histogram equalization is used to adjust contrast; and finally, grayscale normalization is performed according to the DICOM standard. 16-bit color depth is preserved during processing to ensure no loss of cell morphology details.

[0052] S4. When a specific cell of a preset type is detected in the cell image, the detected specific cell is cropped from the cell image and the detected specific cell is counted based on its type.

[0053] S4.1 Receive the preliminary identification results of the preset type-specific cells output by the image detection algorithm, perform secondary verification on the preliminary detection results, eliminate false detection targets, confirm the real specific cells, accurately extract the image region containing specific cells from the original cell image, extract key identification parameters such as morphological features and texture features from the extracted cell image, compare the extracted features with the preset cell type feature library, confirm the specific type of each detected cell, and count the number of specific cells of each type.

[0054] Furthermore, the preliminary cell identification results of the image detection algorithm, which are specific to the preset cell type, are fully received. The result data includes the center coordinates, boundary contours, and preliminary classification confidence scores for each candidate target. For example, the confidence score range for neutrophil candidate targets is 0.7-0.9, and the confidence score range for abnormal cell candidate targets is 0.6-0.8. Multi-dimensional verification is performed on the preliminary detection results: first, it checks whether the morphological parameters conform to the preset range (e.g., whether the cell nucleus diameter is between 7-12 μm); then, it verifies whether the texture features match (e.g., whether the granular texture feature value of neutrophils is greater than the threshold of 0.65); finally, it checks whether the staining characteristics are consistent (e.g., whether the cytoplasmic staining intensity is within the preset range). Targets that pass the verification are marked as positive, and targets that fail are excluded.

[0055] It should be noted that, based on the coordinate information of confirmed positive cells, a local region containing intact cells is precisely cropped from the original cell image. The cropping range is based on the cell center and extends outward by a region twice the cell diameter to ensure the preservation of complete cell morphology and surrounding environment information. The cropped image is saved as a separate file with the same resolution as the original image. Multiple feature parameters are extracted from the cropped cell image: morphological features include cell area, perimeter, roundness, and nucleocytoplasmic ratio; texture features are calculated using the gray-level co-occurrence matrix to determine contrast, correlation, and energy value; staining features are decomposed into RGB three-channel intensity distribution. All feature parameters are normalized to form a standardized feature vector, which is then compared with a preset cell type feature library for similarity. The feature library contains standard feature ranges for various cell types; for example, the standard nucleocytoplasmic ratio range for lymphocytes is 0.2-0.4, and the texture energy value range for macrophages is 0.3-0.6. The final classification result is confirmed when the feature matching degree exceeds the type determination threshold (e.g., cosine similarity > 0.8).

[0056] S5. Record the location information of the detected specific cells in the cell image.

[0057] S5.1. Establish a standardized coordinate system based on the full-scan image, perform edge detection and contour extraction on the identified specific cells, obtain the precise boundary information of the cells in the image, and obtain the coordinates of the geometric center point of each specific cell based on the extracted cell contour. Using the center point as the reference, generate the coordinates of the bounding box of the outer rectangle, and convert the absolute coordinates into standardized relative position parameters relative to the full-scan image.

[0058] Furthermore, based on the physical size and resolution parameters of the full-scan image, a Cartesian coordinate system is established with the top-left corner of the image as the origin (0, 0), the positive X-axis pointing to the right, and the positive Y-axis pointing downwards. The coordinate system uses micrometers (μm) as the basic unit to ensure the comparability of positional parameters between images of different resolutions. For example, for an image with a resolution of 0.25 μm / pixel, each pixel corresponds to a 0.25 μm unit length in the coordinate system. The Canny edge detection algorithm is applied to the identified specific cell regions. First, the image is smoothed using a Gaussian filter (e.g., using a Gaussian kernel with σ = 1.5). Then, the image gradient magnitude and direction are calculated, and continuous cell boundary contours are extracted through non-maximum suppression and double thresholding. The edge detection process retains sub-pixel accuracy, with boundary localization errors controlled within ±0.5 μm. Closed cell contour curves are extracted from the edge detection results, and the Douglas-Peucker algorithm is used to approximate the contours into polygons, reducing the number of vertices while preserving shape features. The contour extraction results are recorded as an ordered set of points. For example, the contour of a typical lymphocyte may consist of 60 to 80 vertex coordinates.

[0059] It should be noted that, based on the extracted cell outline polygon, the centroid coordinates are calculated using the geometric moment method. Using the geometric center point as a reference, the coordinates are expanded outwards along the X and Y axes respectively to find the smallest rectangle that can completely enclose the cell outline. The bounding box is recorded as the coordinates of four vertices, and the absolute coordinates are converted into standardized relative position parameters relative to the entire image.

[0060] S6. When the cell image is opened, the detected specific cells are marked based on the location information.

[0061] S6.1. Obtain the recorded specific cell location information metadata, set the visualization parameters such as marker symbol, color and size according to the user's preset marker style requirements, accurately match and calibrate the stored location coordinates with the currently displayed image coordinate system, generate corresponding marker graphic elements based on location information and style parameters, and automatically adjust the detail of the marker elements according to the image display level for marking.

[0062] Furthermore, the system fully extracts the recorded metadata of specific cell location information from the audit task configuration database. This metadata includes fields such as the geometric center coordinates, bounding box parameters, and relative position percentage for each cell. Based on the visualization parameters preset by the user through the marker style settings interface, the display attributes of various marker elements are configured. Marker symbols can be basic shapes such as solid circles, arrows, or squares. Color parameters use RGB format; for example, the color for lymphocyte markers might be set to (0, 255, 0). Size parameters are associated with the image scaling ratio; at 40x magnification, the marker diameter is set to 30 pixels by default. The stored absolute position coordinates are spatially aligned and calibrated with the currently displayed image view. The calibration process considers image translation, scaling, and rotation, calculating screen coordinates using an affine transformation matrix to ensure that the deviation between the marker position and the actual cell position does not exceed ±1 pixel. For example, the stored (1234.56μm, 789.01μm) is mapped to the current view's (512, 384) pixel coordinates.

[0063] It should be noted that, based on the calibrated coordinates and style parameters, vector-format marker graphic elements are generated. The marker elements include the main graphic (such as a circular marker), auxiliary annotations (such as type abbreviations), and interactive hotspots. Layered drawing technology is used to ensure independent control. For example, a neutrophil marker may consist of a red solid circle, a central N-letter, and an outer transparent response area. The visual appearance of the marker elements is dynamically adjusted according to the current image display level: the complete marker graphic and text annotation are displayed at high magnification; at low magnification, it is simplified to a small-sized solid color marker.

[0064] This embodiment also provides cell smear review, apparatus, computer equipment and storage medium, including: the preset module, used to preset the specific cell types that need to be focused on for the cell smear;

[0065] The acquisition module is used to acquire cell images obtained by scanning the entire cell smear, and to detect the cell images using an image detection algorithm;

[0066] The recording module is used to extract the detected specific cells from the cell image and count the detected specific cells based on their type when a specific cell of a preset type is detected in the cell image, and to record the location information of the detected specific cells in the cell image.

[0067] The labeling module is used to label the detected specific cells based on the location information when the cell image is opened.

[0068] This embodiment also provides a computer device applicable to the cell smear review 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 cell smear review method proposed in the above embodiment.

[0069] 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.

[0070] This embodiment also provides a storage medium storing a computer program, which, when executed by a processor, implements the cell smear review 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.

[0071] In summary, this invention utilizes image detection algorithms to detect cells in cell images corresponding to cell smears, automatically identifying and counting specific cell types of interest. This reduces omissions, effectively improves data integrity and accuracy, and enhances the efficiency of cell smear review. Furthermore, by recording the location information of detected specific cells in the cell image, this application can mark the locations of specific cell types, effectively improving review efficiency and ensuring the reliability of cell smear review.

[0072] Example 2, the second embodiment of the present invention, provides a method for reviewing cell smears to further verify the technical solution of the present invention:

[0073] Figure 1 This diagram illustrates an application scenario of a cell smear review method provided in one embodiment of this application. Figure 1 As shown, both the cell detection device 101 and the scanner 102 can transmit data via a network. The scanner 102 scans cell smears to obtain cell images and transmits these images to the cell detection device 101. The cell detection device 101 pre-defines specific cell types of interest for the cell smears. After acquiring cell images, the device uses an image detection algorithm to detect the cells. When a pre-defined type of specific cell is detected in the cell image, the device extracts the detected specific cell from the image, counts the detected specific cells based on their type, and records their position information within the cell image. When the cell image is opened, the detected specific cells are marked based on their position information.

[0074] This application provides a method for reviewing cell smears, such as... Figure 2 As shown, the method includes the following steps:

[0075] Step S210: Preset the specific cell types that need to be considered for the cell smear.

[0076] Since different cell types often require attention during the review of cell smears for different types of diseases, this application allows for the pre-setting of specific cell types to be considered in the cell smear before review, so that the cell smear can be reviewed in a targeted manner.

[0077] In one implementation, a cell type preset button can be set in the interface. In response to clicking the cell type preset button for cell smears, a cell type preset interface is provided, in which a list of all cell types is displayed, and a checkbox is displayed next to each cell type for the user to select. In response to clicking the OK button on the cell type preset interface, the selected cell type becomes the specific cell type that needs to be focused on for the cell smear.

[0078] Figure 3 This is a schematic diagram of the cell type preset interface in the cell smear review method provided in this application. When it is necessary to set the specific cell types that need to be focused on in the cell smear, the user can click the cell type preset button. In response to the click operation of the cell type preset button for the cell smear, the server provides, as follows: Figure 3 The preset interface for cell types is shown; for example... Figure 3 As shown, a list of all cell types is displayed in the cell type preset interface, and a checkbox is displayed next to each cell type for the user to select. In response to the click of the OK button on the cell type preset interface, the selected cell type becomes the specific cell type that needs to be focused on for the cell smear.

[0079] Step S220: Obtain cell images obtained by scanning the entire cell smear, and use an image detection algorithm to detect the cell images.

[0080] Cell images are obtained by scanning cell smears, providing a basis for subsequent review.

[0081] Step S230: When a specific cell of a preset type is detected in the cell image, the detected specific cell is cropped from the cell image and counted based on the type of the detected specific cell, and the position information of the detected specific cell in the cell image is recorded.

[0082] Step S240: When the cell image is opened, the detected specific cells are labeled based on the location information.

[0083] Specifically, Figure 4 A schematic diagram illustrating cell labeling in the cell smear review method provided in this application is shown below. Figure 4 As shown, when a cell image is opened, the server can mark the detected specific cells based on the previously recorded location information, and the user can quickly verify the cell type and quantity based on the marked specific cells.

[0084] In existing technologies, the review of cell smears involves manual observation to identify specific cell types of interest, followed by manual counting when such types are observed. However, manual observation is prone to omissions, affecting the completeness and accuracy of the data. Furthermore, when secondary verification of specific cell types is required, relocation is time-consuming, hindering rapid and accurate verification and impacting data reliability. In addition, manual observation and counting are slow, significantly affecting review efficiency.

[0085] To address the aforementioned issues, this application proposes a cell smear review method. This method involves: acquiring a pre-defined set of specific cell types to focus on in the cell smear; obtaining a cell image obtained by scanning the entire cell smear; and using an image detection algorithm to detect cells in the image. When a pre-defined type of specific cell is detected in the cell image, the detected specific cells are cropped and counted, and their position information within the cell image is recorded. When the cell image is opened, the detected specific cells are marked based on their position information. This application utilizes an image detection algorithm to detect cells in the cell image corresponding to the cell smear, automatically identifying and counting the specific cell types to focus on, reducing omissions, effectively improving data integrity and accuracy, and increasing the efficiency of cell smear review. Furthermore, by recording the position information of the detected specific cells in the cell image, this application can mark the locations of specific cell types, effectively improving review efficiency and ensuring the reliability of cell smear review.

[0086] Figure 5 This is a schematic diagram of a cell smear review device according to an embodiment of the present invention, such as... Figure 5 As shown, a cell smear review device 30 is provided, which includes a preset module 31, an acquisition module 32, a recording module 33 and a marking module 34;

[0087] Preset module 31 is used to preset the specific cell types that need to be considered for cell smears;

[0088] The acquisition module 32 is used to acquire cell images obtained by scanning the entire cell smear and to detect the cell images using an image detection algorithm.

[0089] The recording module 33 is used to extract the detected specific cells from the cell image and count the detected specific cells based on the type of the detected specific cells when a preset type of specific cell is detected in the cell image, and record the position information of the detected specific cells in the cell image.

[0090] The labeling module 34 is used to label specific cells detected based on location information when a cell image is opened.

[0091] The aforementioned cell smear review device 30 acquires report templates for different disease types. Each report template includes a report name, report triggering conditions, examination findings, and review comments. The examination findings specify the types of required examination data and their corresponding data entry positions. In response to the selection of the automatic trigger button for a report template, it displays the report name for the current examination item whose data meets the report triggering conditions. In response to the selection of a report name, it provides a report confirmation page corresponding to the selected report name. The report confirmation page includes the examination findings and review comments corresponding to the selected report name, and fills in the corresponding examination data in the data entry positions for the examination findings. In response to the selection of the confirmation button on the report confirmation page, it outputs the medical examination report for the current examination item according to a preset format. The medical examination report includes the examination findings and review comments. This application, by setting report triggering conditions in report templates for different disease types, selects report templates whose examination data meets the report triggering conditions after the automatic trigger button is selected, and automatically fills in the required examination data for the examination findings in the corresponding positions. This effectively avoids data entry errors and thus effectively improves the efficiency and accuracy of issuing medical examination reports.

[0092] In one embodiment, the preset module 31 is further configured to provide a cell type preset interface in response to a click operation of the cell type preset button for the cell smear. A list of all cell types is displayed in the cell type preset interface, and a check box is displayed after each cell type for the user to select. In response to a click operation of the confirm button on the cell type preset interface, the selected cell type becomes the specific cell type that needs to be focused on for the cell smear.

[0093] 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.

[0094] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 6 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 stored 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 cell smear review method.

[0095] 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 cell smear review method. The display screen of the computer device may be a liquid crystal display (LCD) or an electronic 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.

[0096] Those skilled in the art will understand that Figure 6 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.

[0097] 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:

[0098] Preset specific cell types to focus on in cell smears;

[0099] The cell images obtained by scanning the entire cell smear are then used to detect the cells using an image detection algorithm.

[0100] When a specific cell of a preset type is detected in a cell image, the detected specific cell is cropped from the cell image, the detected specific cell is counted based on its type, and the location information of the detected specific cell in the cell image is recorded.

[0101] When a cell image is opened, specific cells detected are labeled based on location information.

[0102] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0103] In response to the click of the cell type preset button for cell smears, a cell type preset interface is provided, in which a list of all cell types is displayed, and a checkbox is displayed next to each cell type for the user to select.

[0104] In response to clicking the "OK" button on the cell type preset interface, the selected cell type becomes the specific cell type that needs to be focused on for the cell smear.

[0105] The aforementioned storage medium acquires a preset specific cell type that needs to be considered for the cell smear; acquires a cell image obtained by scanning the entire cell smear; and uses an image detection algorithm to detect the cell image. When a preset type of specific cell is detected in the cell image, the detected specific cell is cropped and counted from the cell image, and the position information of the detected specific cell in the cell image is recorded. When the cell image is opened, the detected specific cell is marked based on the position information.

[0106] 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 cell smears, characterized in that: include, Preset specific cell types that need to be considered for the cell smear; A cell image is obtained by scanning the entire cell smear, and the cell image is detected using an image detection algorithm; When a specific cell of a preset type is detected in the cell image, the detected specific cell is cropped from the cell image and counted based on the type of the detected specific cell, and the location information of the detected specific cell in the cell image is recorded. When the cell image is opened, the detected specific cells are labeled based on the location information.

2. The cell smear review method as described in claim 1, characterized in that: In response to a click operation on the cell type preset button for the cell smear, a cell type preset interface is provided, in which a list of all cell types is displayed, and a checkbox is displayed next to each cell type for the user to select. In response to the click of the "OK" button on the preset cell type interface, the selected cell type becomes the specific cell type that needs to be focused on for the cell smear.

3. The cell smear review method as described in claim 2, characterized in that: The steps include: Pre-setting specific cell types to focus on in the cell smear; and defining the specific cell types to be considered. The user clicks the preset button to activate the cell type selection interface. The system responds to the operation and loads the preset function module. The preset interface fully displays a list of all available cell types. Each option is equipped with an interactive checkbox control. The user specifies the specific cell types to focus on by checking the boxes, forming a preliminary selection set. The user clicks the OK button to complete the selection. The confirmed cell type set is captured and set as the core parameter of the current review task, and then passed to the detection algorithm module.

4. The cell smear review method as described in claim 3, characterized in that: The process involves acquiring cell images from a full-slide scan of the cell smear, and then detecting the cells using an image detection algorithm. This includes the following steps: The scanning device is activated and the parameters are calibrated to prepare for a full-slide scan of the cell smear. The high-precision scanner performs the full-slide scan, converting the physical smear into a high-resolution digital image. The original scanned image is subjected to noise reduction, contrast adjustment, and standardization to improve image quality. The corresponding image recognition algorithm and parameter configuration are automatically loaded according to the preset cell type. Multi-dimensional feature extraction is performed on the optimized image to identify potential cell morphological features and locate specific cells in the image that meet the preset conditions.

5. The cell smear review method as described in claim 4, characterized in that: When a preset type of specific cell is detected in the cell image, the detected specific cell is cropped from the cell image and counted based on its type, including the following steps: The system receives the preliminary identification results of the preset type-specific cells output by the image detection algorithm, performs secondary verification on the preliminary detection results, eliminates false detection targets, confirms the real specific cells, accurately extracts the image region containing specific cells from the original cell image, extracts key identification parameters such as morphological features and texture features from the extracted cell image, compares the extracted features with the preset cell type feature library, confirms the specific type of each detected cell, and counts the number of specific cells of each type.

6. The cell smear review method as described in claim 5, characterized in that: And record the location information of the detected specific cells in the cell image, including the following steps, A standardized coordinate system is established based on the full-scan image. Edge detection and contour extraction are performed on the identified specific cells to obtain the precise boundary information of the cells in the image. Based on the extracted cell contours, the coordinates of the geometric center point of each specific cell are obtained. Using the center point as a reference, the coordinates of the bounding box of the outer rectangle are generated, and the absolute coordinates are converted into standardized relative position parameters relative to the full-scan image.

7. The cell smear review method as described in claim 6, characterized in that: When the cell image is opened, the detected specific cells are labeled based on the location information. Includes the following steps, The system acquires the recorded metadata of specific cell location information, sets visualization parameters such as marker symbols, colors, and sizes according to the user's preset marker style requirements, accurately matches and calibrates the stored location coordinates with the currently displayed image coordinate system, generates corresponding marker graphic elements based on the location information and style parameters, and automatically adjusts the level of detail of the marker elements according to the image display level before marking.

8. A cell smear review apparatus, computer equipment, and storage medium, based on the cell smear review method according to any one of claims 1 to 7, characterized in that: include, The preset module is used to preset the specific cell types that need to be considered for the cell smear; The acquisition module is used to acquire cell images obtained by scanning the entire cell smear, and to detect the cell images using an image detection algorithm; The recording module is used to extract the detected specific cells from the cell image and count the detected specific cells based on their type when a preset type of specific cell is detected in the cell image, and to record the location information of the detected specific cells in the cell image. The labeling module is used to label the detected specific cells based on the location information when the cell image is opened.

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 cell smear review 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 cell smear review method according to any one of claims 1 to 7.

Images