Methods, systems, apparatus, storage media, and products for detecting megakaryocytes

Abstract

This application discloses a method, system, device, storage medium, and product for detecting megakaryocytes, comprising: acquiring pathological slide images and preprocessing the pathological slides, wherein the preprocessing further includes generating small-sized pathological slides based on the pathological slides; inputting the preprocessed pathological slides into a pre-trained segmentation model to output megakaryocyte information and location information; stitching the small pathological slides to generate a high-resolution pathological slide image; inputting the high-resolution pathological slide image into a classification model to output megakaryocyte classification results; acquiring megakaryocyte clustering information based on the high-resolution pathological slide image, and generating medical information based on the megakaryocyte information and location information, the megakaryocyte classification results, and the megakaryocyte clustering information. This method solves the problems of low accuracy and long reading time in manual review of megakaryocyte slides.

Description

Technical Field

[0001] This application generally relates to the field of cell analysis technology, and specifically to a method, system, device, storage medium, and product for detecting megakaryocytes. Background Technology

[0002] In recent years, the incidence of essential thrombocythemia has been gradually increasing. This disease is a myeloproliferative disorder characterized by bleeding tendency and thrombosis, persistent and significant increase in peripheral blood platelets with abnormal function, and excessive proliferation of megakaryocytes in the bone marrow. Among these, the morphology and clustering of megakaryocytes in the bone marrow are important indicators for diagnosing the disease.

[0003] In existing technologies, pathological slides are typically reviewed manually to assess the morphology and clustering of megakaryocytes in patients. However, manual review is often highly subjective, resulting in low diagnostic accuracy and time-consuming slide reading. Summary of the Invention

[0004] In view of the above-mentioned defects or deficiencies in the prior art, it is desirable to provide a method, system, device, storage medium and product for detecting megakaryocytes.

[0005] On the one hand, this application provides a method for detecting megakaryocytes, including:

[0006] The pathological slide images are acquired and the pathological slides are preprocessed to obtain pathological slides with trabeculae removed. The preprocessing also includes generating small-sized pathological slides based on the pathological slides.

[0007] The pre-processed pathological slides are input into a pre-trained segmentation model, which outputs megakaryocyte information and location information to determine whether the pathological slide image contains megakaryocytes.

[0008] The small pathological sections are stitched together to generate high-resolution pathological section images;

[0009] The high-resolution pathological slide image is input into the classification model, and the megakaryocyte classification result is output. The high-resolution slide image is scaled to a preset size according to the megakaryocyte information and location information.

[0010] Megakaryotic cell clustering information is obtained based on the high-resolution pathological slide images, and medical information is generated based on the megakaryotic cell information and location information, the megakaryotic cell classification results, and the megakaryotic cell clustering information to determine the disease.

[0011] Furthermore, pathological slide images are acquired and preprocessed to obtain pathological slides with trabeculae removed. The preprocessing further includes generating smaller pathological slides based on the existing pathological slides, and also includes:

[0012] The pathological sections were converted into RGB color space images;

[0013] The RGB color space image is converted into an HSV format image, and the pathological slides are filtered based on hue, saturation, and brightness to obtain pathological slides with trabeculae removed.

[0014] Furthermore, based on the megakaryocyte information and location information, and the high-resolution pathological slide image, megakaryocyte clustering information is obtained, and medical information is generated based on the megakaryocyte information and location information, the megakaryocyte classification results, and the megakaryocyte clustering information to diagnose the disease, the method further includes:

[0015] Based on the megakaryocyte information and location information, determine the center point coordinates and outline coordinates of the megakaryocyte;

[0016] Determine whether the distance between the center point coordinates and the contour coordinates is less than a preset threshold;

[0017] When the distance between the center point coordinates and the contour coordinates is less than a preset threshold, megakaryocyte clustering information is obtained.

[0018] Furthermore, the high-resolution pathological slide image is input into a classification model to output megakaryocyte classification results. The high-resolution slide image is scaled to a preset size based on the megakaryocyte information and location information. The method also includes:

[0019] The classification results include one of the following: naked megakaryocytes, anucleate megakaryocytes, highly segmented megakaryocytes, and lowly segmented megakaryocytes.

[0020] Secondly, this application provides a detection system for megakaryocytes, the system comprising:

[0021] A preprocessing module is used to acquire pathological slide images and preprocess the pathological slides to obtain pathological slides with trabeculae removed. The preprocessing also includes generating small-sized pathological slides based on the pathological slides.

[0022] The segmentation module is used to input the pre-processed pathological slides into a pre-trained segmentation model and output megakaryocyte information and location information to determine whether the pathological slide image contains megakaryocytes.

[0023] A stitching module is used to stitch together the small pathological slides to generate high-resolution pathological slide images;

[0024] The classification module is used to input the high-resolution pathological slide image into the classification model and output the megakaryocyte classification result, wherein the high-resolution slide image is scaled to a preset size according to the megakaryocyte information and position information;

[0025] The information acquisition module is used to acquire megakaryocyte cluster information based on the high-resolution pathological slide image, and generate medical information based on the megakaryocyte information and location information, the megakaryocyte classification results, and the megakaryocyte cluster information to make a diagnosis.

[0026] Furthermore, the preprocessing module is also used for:

[0027] The pathological sections were converted into RGB color space images;

[0028] The RGB color space image is converted into an HSV format image, and the pathological slides are filtered based on hue, saturation, and brightness to obtain pathological slides with trabeculae removed.

[0029] Furthermore, the information acquisition module is also used for:

[0030] Based on the megakaryocyte information and location information, determine the center point coordinates and outline coordinates of the megakaryocyte;

[0031] Determine whether the distance between the center point coordinates and the contour coordinates is less than a preset threshold;

[0032] When the distance between the center point coordinates and the contour coordinates is less than a preset threshold, megakaryocyte clustering information is obtained.

[0033] Thirdly, this application provides a megakaryocyte detection device, including a processor and a memory, wherein the memory stores at least one instruction, at least one program, code set, or instruction set, and the instruction, program, code set, or instruction set is loaded by the processor and executed according to any one of the embodiments of this application for megakaryocyte detection.

[0034] Fourthly, this application provides a non-transitory computer-readable storage medium, characterized in that, when the instructions in the storage medium are executed by the processor of a mobile terminal, the mobile terminal is able to execute the megakaryocyte detection method according to any one of the embodiments of this application.

[0035] Fifthly, this application provides a computer program product that, when the instructions in the computer program product are executed by the processor of a mobile terminal, enables the mobile terminal to perform the megakaryocyte detection method according to any one of the embodiments of this application.

[0036] In summary, the megakaryocyte detection method, system, device, storage medium, and product based on the present invention improve the high resolution of pathological slides by processing them, and determine the morphology and clustering of megakaryocytes in patients based on a classification model, thus ensuring the objectivity of megakaryocyte detection. Attached Figure Description

[0037] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0038] Figure 1 A flowchart illustrating a method for detecting megakaryocytes provided for embodiments of this application;

[0039] Figure 2 Schematic diagrams of pathological sections before and after trabecular bone removal, provided for embodiments of this application;

[0040] Figure 3 Images of pathological slides cut to half their original size, provided for embodiments of this application;

[0041] Figure 4 A schematic diagram of megakaryocyte classification results provided for embodiments of this application;

[0042] Figure 5 A schematic diagram illustrating megakaryocyte clustering determination provided for embodiments of this application;

[0043] Figure 6 A schematic diagram illustrating the determination of megakaryocytes provided for embodiments of this application;

[0044] Figure 7 A schematic diagram of the megakaryocyte segmentation process provided for embodiments of this application;

[0045] Figure 8 A flowchart illustrating the megakaryocyte classification process provided for embodiments of this application;

[0046] Figure 9 A structural block diagram of a megakaryocyte detection system provided for embodiments of this application;

[0047] Figure 10 A schematic diagram of the structure of a megakaryocyte detection device provided in an embodiment of this application. Detailed Implementation

[0048] The present application will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings.

[0049] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0050] This application generally relates to the field of cell analysis technology, thereby improving the objectivity of megakaryocyte detection. The following embodiments of this application exemplify the training method of an antiviral drug relocation model.

[0051] See details Figure 1 This application provides a method for detecting megakaryocytes, comprising:

[0052] S101, acquire pathological slide images and preprocess the pathological slides to obtain pathological slides with trabeculae removed, wherein the preprocessing further includes generating small-sized pathological slides based on the pathological slides.

[0053] Specifically, the cellular tissue area is scanned into pathological slide images using a scanner. However, the obtained pathological slides are usually not convenient for examination and contain cells and tissues that interfere with the test results, so preprocessing of the pathological slides is necessary.

[0054] Because a single pathological slide image is extremely large, with a resolution potentially reaching 100,000 × 100,000, it cannot be used directly. Therefore, the image needs to be processed to create multiple smaller pathological slides of a specific size. During this processing, the cutting step is not the actual size of the smaller slide, but rather one-half or three-quarters of its original size. Figure 3 As shown, although this increases the number of small pathological sections to be cut, it ensures the integrity of the cell outline in the final result.

[0055] In some embodiments, pathological slide images are acquired and preprocessed to obtain pathological slides with trabeculae removed. The preprocessing further includes generating smaller pathological slides based on the pathological slides, and also includes:

[0056] The pathological sections were converted into RGB color space images;

[0057] The RGB color space image is converted into an HSV format image, and the pathological slides are filtered based on hue, saturation, and brightness to obtain pathological slides with trabeculae removed.

[0058] Specifically, trabeculae are extensions of the cortical bone within cancellous bone, and these trabeculae can affect a physician's interpretation of pathological sections. The acquired pathological section images are converted to RGB format, then to HSV format. Trabeculae are removed by filtering through a first preset threshold value across the h, s, and v channels of the HSV format, followed by a second preset threshold value across the h, s, and v channels to ensure accurate trabeculae removal. The HVS format pathological section image after this second trabeculae removal is then converted back to RGB format to obtain a trabeculae-removed pathological section image, as shown below. Figure 2 As shown.

[0059] S102, the pre-processed pathological slides are input into a pre-trained segmentation model, which outputs megakaryocyte information and location information to determine whether the pathological slide image contains megakaryocytes.

[0060] Specifically, segmentation models in the medical field include those with relatively deep network layers, such as TransUNet and U2Net. TransUNet is the preferred segmentation model here. TransUNet incorporates transformers, allowing the segmentation model to better focus on both overall and local information in pathological slide images, thus improving the accuracy of megakaryocyte detection.

[0061] The processed pathological slide images are fed into a segmentation model to predict and obtain a binary image (mask) with 0 and 255 pixel values, in order to determine whether the cell contains a megakaryocyte. Figure 6 As shown. Simultaneously, the coordinates of the processed pathological slide images are generated, facilitating the merging of the predicted mask images into the original positions based on these coordinates.

[0062] Pre-prepared training data, labeled by pathologists, is input into the segmentation model for training. This data ensures accuracy and improves the model's segmentation accuracy. During preprocessing, large pathological slides are cut into images of a preset size. Due to the low density of megakaryocytes and to ensure sufficient training of the segmentation model, each image is designed to contain megakaryocytes. This allows the model to output the shape of cells in the slide and determine cell type after the pathological slide is input. Figure 6 As shown, this allows us to determine whether the pathological section contains megakaryocytes.

[0063] For example, such as Figure 7 As shown, using a pre-prepared TransUNet with transformer added, the model can better focus on the overall and local information of pathological slide images.

[0064] S103, the small pathological sections are stitched together to generate a high-resolution pathological section image.

[0065] Specifically, the small-sized pathological slices segmented by the segmentation model are stitched together to form a high-resolution image (mask) with the same size as the original pathological slices.

[0066] S104, the high-resolution pathological slide image is input into the classification model, and the megakaryocyte classification result is output, wherein the high-resolution slide image is scaled to a preset size according to the megakaryocyte information and location information.

[0067] Specifically, the ResNet series of deep learning models is preferentially used as the classification model here. The ResNet series incorporates residual modules. Typically, as the complexity of classification tasks increases, the number of network layers is naturally increased. However, this can lead to gradient vanishing during training. The residual modules introduced in the ResNet model effectively solve this problem. Therefore, the locations of megakaryocytes in high-resolution pathological sections are scaled to a preset size and then input into the classification model to obtain the classification results. This preset size can be dynamically adjusted based on the experimenter's experience.

[0068] In some embodiments, the high-resolution pathological slide image is input into a classification model to output megakaryocyte classification results, wherein the high-resolution slide image is scaled to a preset size according to the megakaryocyte information and location information, and further includes:

[0069] The megakaryocyte classification results include one of the following: naked megakaryocytes, anucleate megakaryocytes, highly segmented megakaryocytes, and lowly segmented megakaryocytes.

[0070] Specifically, megakaryocytes are cells in the bone marrow that differentiate from hematopoietic stem cells. They are mature platelet-producing cells in normal bone marrow, and their precursor is the granular megakaryocyte. These cells are enormous; when mature megakaryocytes rupture and detach from their periphery, they form platelets. On average, each megakaryocyte can produce 2000 platelets. They are generally classified into naked megakaryocytes, anucleate megakaryocytes, highly segmented megakaryocytes, and lowly segmented megakaryocytes. For example, this classification result is as follows: Figure 4 As shown, the square boxes represent high-lobed megakaryocytes, and the circular boxes represent low-lobed megakaryocytes.

[0071] For example, such as Figure 8 As shown, the ResNet series of deep models are used, and residual modules are added to classify pre-prepared high-resolution pathological slide images.

[0072] S105, obtain megakaryocyte clustering information based on the high-resolution pathological slide image, and generate medical information based on the megakaryocyte information and location information, the megakaryocyte classification result, and the megakaryocyte clustering information to determine the disease.

[0073] Specifically, medical information is generated based on megakaryocyte information and location information, megakaryocyte clustering information, and megakaryocyte classification results. This medical information can help doctors quickly locate and distinguish the location, type, and clustering of megakaryocytes for diagnosis, thereby assisting doctors in making a diagnosis of essential thrombocytosis.

[0074] In some embodiments, megakaryocyte clustering information is obtained based on the high-resolution pathological slide images, and medical information is generated based on the megakaryocyte information and location information, the megakaryocyte classification results, and the megakaryocyte clustering information to determine the disease, further comprising:

[0075] Based on the megakaryocyte information and location information, determine the center point coordinates and outline coordinates of the megakaryocyte;

[0076] Determine whether the distance between the center point coordinates and the contour coordinates is less than a preset threshold;

[0077] When the distance between the center point coordinates and the contour coordinates is less than a preset threshold, megakaryocyte clustering information is obtained.

[0078] Specifically, the original image is magnified to a preset magnification. Based on the megakaryocyte information and location information, the outline coordinates of the megakaryocytes on the pathological slide image after magnification are found, along with the coordinates of the center point of the megakaryocyte outline. The distances between the center point coordinates of the megakaryocyte outline and the center point coordinates of other cell outlines in the pathological slide image are iterated, and it is determined whether the distance meets the actual distance threshold. If it does, the cell is identified as potentially belonging to a cluster, and the coordinates of all cells that may form a cluster with this cell are placed in the same list, i.e., such as... Figure 5 As shown, information on megakaryocyte clustering is generated.

[0079] In other embodiments, it is also necessary to further determine whether a cluster is formed. For example, if cell A and cell B meet the distance requirement, and cell B and cell C also meet the distance requirement, then it is also necessary to determine that cells A and C meet the distance requirement for clustering. Then, the result containing three or more cell clusters is determined to be a cluster.

[0080] In summary, the megakaryocyte detection method based on the present invention improves the resolution of pathological sections by processing them, and judges the morphology and clustering of megakaryocytes in patients based on a classification model, thus ensuring the objectivity of megakaryocyte detection.

[0081] Further reference Figure 9 The diagram shows a schematic of a megakaryocyte detection system 200 according to an embodiment of this application.

[0082] The preprocessing module 210 is used to acquire pathological slide images and preprocess the pathological slides to obtain pathological slides with trabeculae removed. The preprocessing also includes generating small-sized pathological slides based on the pathological slides.

[0083] The segmentation module 220 is used to input the pre-processed pathological slides into a pre-trained segmentation model and output megakaryocyte information and location information to determine whether the pathological slide image contains megakaryocytes.

[0084] The stitching module 230 is used to stitch the small pathological slides together to generate a high-resolution pathological slide image;

[0085] The classification module 240 is used to input the high-resolution pathological slide image into the classification model and output the megakaryocyte classification result, wherein the high-resolution slide image is scaled to a preset size according to the megakaryocyte information and position information;

[0086] The information acquisition module 250 is used to acquire megakaryocyte cluster information based on the high-resolution pathological slide image, and generate medical information based on the megakaryocyte information and location information, the megakaryocyte classification result, and the megakaryocyte cluster information to make a diagnosis.

[0087] The division of modules or units mentioned in the detailed description above is not mandatory. In fact, according to the embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0088] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operational instructions of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code, which includes one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two connected blocks may actually be executed substantially in parallel, or they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified functions or operational instructions, or using a combination of dedicated hardware and computer instructions. The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of disclosure in this application is not limited to technical solutions formed by specific combinations of the above-mentioned technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-mentioned technical features or their equivalent features without departing from the aforementioned disclosed concept. For example, technical solutions formed by substituting the above-mentioned features with (but not limited to) technical features with similar functions disclosed in this application.

[0089] Further reference Figure 10 The diagram shows a schematic structural diagram of a megakaryocyte detection device 300 according to an embodiment of this application.

[0090] The main body executing the megakaryocyte detection method in this embodiment is a megakaryocyte detection device. The megakaryocyte detection device can be implemented by software and / or hardware. In this embodiment, the megakaryocyte detection device can be configured in an electronic device or in a server used to control the electronic device. The server communicates with the electronic device and controls it.

[0091] In this embodiment, the electronic device may include, but is not limited to, personal computing devices, platform computers, smartphones, etc. This embodiment does not specifically limit the electronic device.

[0092] The megakaryocyte detection device 300 of this embodiment includes a processor and a memory, which are interconnected. The memory is used to store a computer program, which includes program instructions. The processor is configured to call the program instructions to execute the method described in any of the above embodiments.

[0093] In this embodiment, the processor is a processing device capable of performing logical operations, such as a central processing unit (CPU), field-programmable array (FPGA), digital signal processor (DSP), microcontroller (MCU), application-specific logic circuit (ASIC), graphics processing unit (GPU), or other devices with data processing and / or program execution capabilities. It is readily understood that the processor is typically communicatively connected to memory, where any combination of one or more computer program products is stored. The memory can include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, erasable programmable read-only memory (EPROM), USB memory, flash memory, etc. One or more computer instructions can be stored in the memory, and the processor can execute these computer instructions to implement related analysis functions. Various applications and various data, such as various data used and / or generated by applications, can also be stored in the computer-readable storage medium.

[0094] In the embodiments of this application, each module can be implemented by the processor executing relevant computer instructions. For example, the acquisition module can be implemented by the processor executing acquisition instructions, the input module can be implemented by the processor executing rule model instructions, and the neural network can be implemented by the processor executing neural network algorithm instructions.

[0095] In the embodiments of this application, each module can run on the same processor or on multiple processors; each module can run on a processor of the same architecture, such as all running on x86 architecture processors, or it can run on processors of different architectures, such as the image processing module running on an x86 architecture CPU and the machine learning module running on a GPU. Each module can be packaged in a computer product, such as each module being packaged in a computer software and running on a computer (server), or each module or part of it can be packaged in different computer products, such as the image processing module being packaged in a computer software and running on a computer (server), and the machine learning modules being packaged in separate computer software and running on another or more computers (servers); the computing platform when each module executes can be local computing, cloud computing, or a hybrid computing consisting of local computing and cloud computing.

[0096] The computer system includes a central processing unit (CPU) 301, which performs various appropriate actions and processes based on programs stored in read-only memory (ROM) 302 or programs loaded from storage section 308 into random access memory (RAM) 303. RAM 303 also stores various programs and data required for the system's operating instructions. CPU 301, ROM 302, and RAM 303 are interconnected via bus 304. Input / output (I / O) interface 305 is also connected to bus 304.

[0097] The following components are connected to I / O interface 305: an input section 306 including a keyboard, mouse, etc.; an output section 307 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN card, modem, etc. The communication section 309 performs communication processing via a network such as the Internet. Drive 310 is also connected to I / O interface 305 as needed. Removable media 311, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 310 as needed so that computer programs read from them can be installed into storage section 308 as needed.

[0098] Specifically, according to embodiments of this application, the flowchart above refers to... Figure 1 The described process can be implemented as a computer software program. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowchart. In such an embodiment, the computer program contains program code for performing the methods shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via communication section 309, and / or installed from removable medium 311. When the computer program is executed by central processing unit (CPU) 301, it performs the functions defined in the system of this application.

[0099] The electronic device provided in this application embodiment is provided with a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, which is executed by a processor to implement the method as described in any of the above.

[0100] It should be noted that the computer-readable medium shown in this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0101] In one embodiment, a computer program product is provided that, when executed by a processor of an electronic device, enables a megakaryocyte detection device to perform the following steps:

[0102] The pathological slide images are acquired and the pathological slides are preprocessed to obtain pathological slides with trabeculae removed. The preprocessing also includes generating small-sized pathological slides based on the pathological slides.

[0103] The pre-processed pathological slides are input into a pre-trained segmentation model, which outputs megakaryocyte information and location information to determine whether the pathological slide image contains megakaryocytes.

[0104] The small pathological sections are stitched together to generate high-resolution pathological section images;

[0105] The high-resolution pathological slide image is input into the classification model, and the megakaryocyte classification result is output. The high-resolution slide image is scaled to a preset size according to the megakaryocyte information and location information.

[0106] Megakaryotic cell clustering information is obtained based on the high-resolution pathological slide images, and medical information is generated based on the megakaryotic cell information and location information, the megakaryotic cell classification results, and the megakaryotic cell clustering information to determine the disease.

[0107] It should be understood that the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the present invention.

[0108] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0109] Unless otherwise defined, the technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art. The terminology used herein is for descriptive purposes only and is not intended to limit the invention. Terms such as “set” appearing herein can refer to either a component being directly attached to another component or a component being attached to another component via an intermediary. A feature described in one embodiment herein may be applied, alone or in combination with other features, to another embodiment, unless that feature is not applicable in that other embodiment or is otherwise stated.

[0110] The present invention has been described through the above embodiments; however, it should be understood that the above embodiments are for illustrative purposes only and are not intended to limit the present invention to the described embodiments. Those skilled in the art will understand that many variations and modifications can be made based on the teachings of the present invention, and all such variations and modifications fall within the scope of protection claimed by the present invention.

Claims

1. A method for detecting megakaryocytes, characterized in that, include: The pathological slide images are acquired and the pathological slides are preprocessed to obtain pathological slides with trabeculae removed. The preprocessing also includes generating small-sized pathological slides based on the pathological slides. The pre-processed pathological slides are input into a pre-trained segmentation model, which outputs megakaryocyte information and location information to determine whether the pathological slide image contains megakaryocytes. The small pathological sections are stitched together to generate high-resolution pathological section images; The high-resolution pathological slide image is input into the classification model, and the megakaryocyte classification result is output. The high-resolution slide image is scaled to a preset size according to the megakaryocyte information and location information. Megakaryotic cell clustering information is obtained based on the high-resolution pathological slide images, and medical information is generated based on the megakaryotic cell information and location information, the megakaryotic cell classification results, and the megakaryotic cell clustering information to determine the disease. The step of acquiring pathological slide images and preprocessing the pathological slides to obtain pathological slides with trabeculae removed includes, wherein the preprocessing further includes generating small-sized pathological slides based on the pathological slides, and also includes: The pathological sections were converted into RGB color space images; The RGB color space image is converted to HSV format, and the pathological slide is filtered based on hue, saturation, and brightness to obtain a pathological slide with trabeculae removed. The filtering of the pathological slide based on hue, saturation, and brightness includes: filtering and removing the trabeculae through a preset first threshold of the h, s, and v channels in the HSV format, and then filtering and removing the trabeculae a second time through a preset second threshold of the h, s, and v channels. The pathological slide with trabeculae removed is an RGB format pathological slide image converted from the HVS format pathological slide image with the trabeculae removed a second time.

2. The method for detecting megakaryocytes according to claim 1, characterized in that, Based on the megakaryocyte information and location information, and the high-resolution pathological slide image, megakaryocyte clustering information is obtained. The megakaryocyte classification results and the megakaryocyte clustering information are used to generate medical information for disease diagnosis, and the method further includes: Based on the megakaryocyte information and location information, determine the center point coordinates and outline coordinates of the megakaryocyte; Determine whether the distance between the center point coordinates and the contour coordinates is less than a preset threshold; When the distance between the center point coordinates and the contour coordinates is less than a preset threshold, megakaryocyte clustering information is obtained.

3. The method for detecting megakaryocytes according to claim 1, characterized in that, The high-resolution pathological slide image is input into a classification model, and the megakaryocyte classification result is output. The high-resolution slide image is scaled to a preset size based on the megakaryocyte information and location information. The model also includes: The classification results include one of the following: naked megakaryocytes, anucleate megakaryocytes, highly segmented megakaryocytes, and lowly segmented megakaryocytes.

4. A detection system for megakaryocytes, characterized in that, include: A preprocessing module is used to acquire pathological slide images and preprocess the pathological slides to obtain pathological slides with trabeculae removed. The preprocessing also includes generating small-sized pathological slides based on the pathological slides. The segmentation module is used to input the pre-processed pathological slides into a pre-trained segmentation model and output megakaryocyte information and location information to determine whether the pathological slide image contains megakaryocytes. A stitching module is used to stitch together the small pathological slides to generate high-resolution pathological slide images; The classification module is used to input the high-resolution pathological slide image into the classification model and output the megakaryocyte classification result, wherein the high-resolution slide image is scaled to a preset size according to the megakaryocyte information and position information; The information acquisition module is used to acquire megakaryocyte cluster information based on the high-resolution pathological slide image, and generate medical information based on the megakaryocyte information and location information, the megakaryocyte classification result and the megakaryocyte cluster information to judge the disease. The preprocessing module is further configured to: The pathological sections were converted into RGB color space images; The RGB color space image is converted to HSV format, and the pathological slide is filtered based on hue, saturation, and brightness to obtain a pathological slide with trabeculae removed. The filtering of the pathological slide based on hue, saturation, and brightness includes: filtering and removing the trabeculae through a preset first threshold of the h, s, and v channels in the HSV format, and then filtering and removing the trabeculae a second time through a preset second threshold of the h, s, and v channels. The pathological slide with trabeculae removed is an RGB format pathological slide image converted from the HVS format pathological slide image with the trabeculae removed a second time.

5. The megakaryocyte detection system as described in claim 4, characterized in that, The information acquisition module is also used for: Based on the megakaryocyte information and location information, determine the center point coordinates and outline coordinates of the megakaryocyte; Determine whether the distance between the center point coordinates and the contour coordinates is less than a preset threshold; When the distance between the center point coordinates and the contour coordinates is less than a preset threshold, megakaryocyte clustering information is obtained.

6. A device for detecting megakaryocytes, characterized in that, The method includes a processor and a memory, wherein the memory stores at least one instruction, at least one program, code set, or instruction set, and the instruction, program, code set, or instruction set is loaded and executed by the processor to implement the megakaryocyte detection method according to any one of claims 1-3.

7. A non-transitory computer-readable storage medium, characterized in that, When the instructions in the storage medium are executed by the processor of the mobile terminal, the mobile terminal is able to perform the megakaryocyte detection method according to any one of claims 1-3.

8. A computer program product, characterized in that, When the instructions in the computer program product are executed by the processor of the mobile terminal, the mobile terminal is able to perform the megakaryocyte detection method according to any one of claims 1-3.

Images