Urine exfoliative cytology analysis system and urine exfoliative cytology analysis method

Abstract

The invention relates to a urine exfoliated cytology analysis system. The system comprises an information acquisition platform, an image scanning platform, an image processing module, a heterotypic cell prompting module and a user interaction module, the information acquisition platform provides a basic information filling interface for a user to fill basic information and generate an exclusive two-dimensional code; the image scanning platform is used for planning a scanning path, scanning a slide based on the scanning path, and splicing local cell images into a complete full-slide image; the image processing module is used for positioning, identifying and classifying cells in the full-slide image; the heterotype cell prompting module is used for calculating morphological parameters of the urine cast-off cells, distinguishing the urine cast-off cells based on the morphological parameters, performing highlight labeling on atypical urine cast-off cells and malignant urine cast-off cells and providing a classification result prompt; the user interaction module is used for providing a user interaction interface for a user to check and check the processing result of the heterotype cell prompting module and for the user to fill in an analysis result, so that the urine exfoliative cytology analysis efficiency is improved.

Description

Technical Field

[0001] The present application relates to the technical field of cell detection, and in particular to a urine exfoliated cytology analysis system and a urine exfoliated cytology analysis method. Background Art

[0002] Urine exfoliated cytology plays an indispensable role in the screening of urinary system diseases. By analyzing the morphology of exfoliated cells in urine, it can effectively screen and detect new and recurrent high-risk urothelial cancers, which include bladder, kidney, ureter and urethra. With its advantages of intuitiveness, rapidity, cost-effectiveness and high specificity of up to 85%~100%, urine exfoliated cytology has become one of the most widely used methods for early diagnosis, screening and follow-up of urothelial cancer.

[0003] In the prior art, urine exfoliated cytology examination relies on experienced cytology experts to observe urine exfoliated cytology slides under a microscope to analyze the morphological changes of urine exfoliated cells in urine, and then issue a final diagnosis result based on subjective judgment and accumulated experience. However, cognitive differences among different cytology experts may lead to low consistency in urine exfoliated cytology analysis results, and manual observation and analysis are time-consuming, resulting in low efficiency of urine exfoliated cytology analysis in the prior art.

[0004] With regard to the problem of low efficiency of urine exfoliated cytology analysis caused by manual observation and analysis of urine exfoliated cytology slides in the prior art, no effective solution has been proposed so far. Summary of the invention

[0005] Based on this, it is necessary to provide a urine exfoliated cytology analysis system and a urine exfoliated cytology analysis method to address the above technical issues, so as to solve the problem of low efficiency of urine exfoliated cytology analysis in related technologies.

[0006] In a first aspect, an embodiment of the present application provides a urine exfoliated cytology analysis system, including an information acquisition platform, an image scanning platform, an image processing module, an atypical cell prompting module, and a user interaction module;

[0007] The information collection platform is used to provide a basic information filling interface for users to fill in the basic information of the owner of the urine exfoliated cytology slide and generate an exclusive QR code for the urine exfoliated cytology slide;

[0008] The image scanning platform is used to automatically plan a scanning path according to the size and shape of the urine exfoliated cytology slide with the exclusive QR code posted, scan the urine exfoliated cytology slide based on the scanning path, and seamlessly splice multiple local cell images obtained by scanning into a complete full slide image;

[0009] The image processing module automatically locates, identifies and classifies cells in the whole slide image using an image detection algorithm;

[0010] The atypical cell prompting module calculates the relevant morphological parameters of the urine exfoliated cells identified by the image processing module using a deep learning algorithm, distinguishes normal urine exfoliated cells, atypical urine exfoliated cells, malignant urine exfoliated cells and degenerated cells based on the morphological parameters, and highlights atypical urine exfoliated cells and malignant urine exfoliated cells as atypical cells, and provides corresponding classification result prompt labels; the relevant morphological parameters include the size of the cell nucleus-cytoplasm ratio, the regularity of the nuclear membrane morphology, the fineness of the chromatin, the obviousness of the nucleolus and the depth of the cell nuclear staining;

[0011] The user interaction module is used to provide a user interaction interface for users to view and review the processing results of the atypical cell prompt module and for users to fill in the analysis results.

[0012] In one embodiment, the urine exfoliated cytology analysis system provided by the present application also includes a data storage module, which is respectively connected to the information acquisition platform, the image processing module and the atypical cell prompt module, and the data storage module is used to store the basic information of the owner of the urine exfoliated cytology slide, the whole slide image and the image processing result recognized by the image processing module.

[0013] In one embodiment, the basic information of the owner of the urine exfoliated cytology slide includes ID, name, age and gender.

[0014] In a second aspect, the present application provides a method for urine exfoliated cytology analysis, the method comprising the following steps:

[0015] Providing a basic information filling interface for the user to fill in the basic information of the owner of the urine exfoliated cytology slide, and generating an exclusive QR code for the urine exfoliated cytology slide;

[0016] Automatically planning a scanning path according to the size and shape of the urine exfoliated cytology slide with the exclusive QR code posted, scanning the urine exfoliated cytology slide based on the scanning path, and seamlessly splicing multiple local cell images obtained by scanning into a complete full slide image;

[0017] Automatically locating, identifying and classifying cells in the whole slide image using an image detection algorithm;

[0018] The deep learning algorithm is used to calculate the relevant morphological parameters of the urine exfoliated cells identified by the image processing module, and normal urine exfoliated cells, atypical urine exfoliated cells, malignant urine exfoliated cells and degenerate cells are distinguished based on the morphological parameters, and atypical urine exfoliated cells and malignant urine exfoliated cells are highlighted as atypical cells, and corresponding classification result prompt labels are provided; the relevant morphological parameters include the size of the cell nucleus-cytoplasm ratio, the regularity of the nuclear membrane morphology, the fineness of the chromatin, the prominence of the nucleolus and the depth of the cell nuclear staining;

[0019] A user interaction interface is provided for users to view and review the processing results of the atypical cell prompt module and for users to fill in the analysis results.

[0020] The above-mentioned urine exfoliated cytology analysis system and urine exfoliated cytology analysis method include an information collection platform, an image scanning platform, an image processing module, an atypical cell prompting module and a user interaction module; the information collection platform is used to provide a basic information filling interface for users to fill in the basic information of the owner of the urine exfoliated cytology slide and generate an exclusive QR code for the urine exfoliated cytology slide; the image scanning platform is used to automatically plan the scanning path according to the size and shape of the urine exfoliated cytology slide with the exclusive QR code posted, scan the urine exfoliated cytology slide based on the scanning path, and seamlessly splice the multiple local cell images obtained by scanning into a complete full slide image; the image processing module uses an image detection algorithm to detect the cells in the full slide image Automatic positioning, identification and classification; the atypical cell prompt module uses a deep learning algorithm to calculate the relevant morphological parameters of the urine exfoliated cells identified by the image processing module, distinguishes normal urine exfoliated cells, atypical urine exfoliated cells, malignant urine exfoliated cells and degenerated cells based on the morphological parameters, and highlights atypical urine exfoliated cells and malignant urine exfoliated cells as atypical cells, and provides corresponding classification result prompt labels; the relevant morphological parameters include the size of the nucleus-cytoplasm ratio, the regularity of the nuclear membrane morphology, the fineness of the chromatin, the obviousness of the nucleolus and the depth of the nuclear staining; the user interaction module is used to provide a user interaction interface for users to view and review the processing results of the atypical cell prompt module, and for users to fill in the analysis results. This application introduces artificial intelligence technology to convert traditional urine exfoliated cytology physical slides into digital slides, simplify the process of manual microscopy, abandon the subjectivity and experience dependence of manual reading and the limitations of traditional methods, promote the consistency of urine exfoliated cytology analysis results, and improve the speed, accuracy and sensitivity of urine exfoliated cytology analysis, thereby effectively improving the efficiency of urine exfoliated cytology analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0022] Figure 1 is a schematic diagram of a urine exfoliated cytology analysis system provided according to an embodiment of the present application;

[0023] Figure 2 It is a flow chart of the urine exfoliated cytology analysis method provided according to the embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0025] Obviously, the drawings described below are only some examples or embodiments of the present application. For ordinary technicians in this field, the present application can also be applied to other similar scenarios based on these drawings without creative work. In addition, it can also be understood that although the efforts made in this development process may be complicated and lengthy, for ordinary technicians in this field related to the content disclosed in this application, some changes in design, manufacturing or production based on the technical content disclosed in this application are just conventional technical means, and should not be understood as insufficient content disclosed in this application.

[0026] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0027] Unless otherwise defined, the technical terms or scientific terms involved in this application should be understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the" and the like involved in this application do not indicate a quantity limitation, and may indicate the singular or plural. The terms "include", "comprise", "have" and any of their variations involved in this application are intended to cover non-exclusive inclusions; for example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units that are not listed, or may also include other steps or units inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there may be three relationships, for example, "A and / or B" can mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects before and after are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0028] Figure 1 A schematic diagram of the urine exfoliated cytology analysis system provided in this application, such as Figure 1As shown, the urine exfoliated cytology analysis system 10 includes an information collection platform 11, an image scanning platform 12, an image processing module 13, an atypical cell prompting module 14 and a user interaction module 15; the information collection platform 11 is used to provide a basic information filling interface for users to fill in the basic information of the urine exfoliated cytology slide owner and generate an exclusive QR code for the urine exfoliated cytology slide; the image scanning platform 12 is used to automatically plan a scanning path according to the size and shape of the urine exfoliated cytology slide with the exclusive QR code posted, scan the urine exfoliated cytology slide based on the scanning path, and seamlessly splice the scanned multiple local cell images into a complete full slide image; the image processing module 13 uses an image detection algorithm to detect the full slide image in the full slide image. The cells are automatically located, identified and classified; the atypical cell prompting module 14 uses a deep learning algorithm to calculate the relevant morphological parameters of the urine exfoliated cells identified by the image processing module, distinguishes normal urine exfoliated cells, atypical urine exfoliated cells, malignant urine exfoliated cells and degenerated cells based on the morphological parameters, and highlights atypical urine exfoliated cells and malignant urine exfoliated cells as atypical cells, and provides corresponding classification result prompt labels; the relevant morphological parameters include the size of the cell nucleus-cytoplasm ratio, the regularity of the nuclear membrane morphology, the fineness of the chromatin, the obviousness of the nucleolus and the depth of the cell nucleus staining; the user interaction module 15 is used to provide a user interaction interface for users to view and review the processing results of the atypical cell prompting module, and for users to fill in the analysis results.

[0029] Specifically, the information collection platform 11 in the present application can enter the basic information of the person to be tested, that is, the basic information of the urine exfoliated cytology slide, according to the electronic database of the medical system, and generate an exclusive QR code for the urine exfoliated cytology slide. The basic information of the urine exfoliated cytology slide may include ID, name, age and gender, etc. It should be noted that the exclusive QR code of each urine exfoliated cytology slide is different, and a specific area is reserved on the urine exfoliated cytology slide in the present application for posting the exclusive QR code generated by the information collection platform 11. The image scanning platform 12 in the present application can have a built-in automatic scanning and image stitching algorithm, and can automatically plan the scanning path according to the size and shape of the urine exfoliated cytology slide with the exclusive QR code posted, scan the urine exfoliated cytology slide based on the scanning path, and seamlessly stitch the scanned multiple local cell images into a complete full slide image. And the image scanning platform 12 in the present application can use a high-precision stepper motor to drive the scanning platform, and adopt an anti-vibration design to ensure the smooth movement and clear image acquisition of the urine exfoliated cytology slide during the scanning process. The image scanning platform 12 can also integrate a high-resolution imaging system, equipped with a high-precision optical lens and a high-sensitivity camera, so that the structural details of each cell in the urine exfoliated cytology slide can be cleanly captured. In addition, the image scanning platform 12 can also use a multi-spectral light source, which can automatically adjust the light source intensity and color according to the staining condition and detection requirements of the urine exfoliated cytology slide to optimize the image quality. The image processing module 13 in the present application can integrate a deep learning framework, using the Faster R-CNN target detection algorithm, combined with transfer learning, data enhancement technology and support vector machine (SVM) algorithm, for feature extraction and pattern recognition of cell images to identify different types of cells, including urine exfoliated cells, broken cells, inflammatory cells, squamous cells, blood cells, crystals, impurities, to achieve automatic image annotation and classification functions, reduce manual intervention, and improve the efficiency and accuracy of image processing. The atypical cell prompt module 14 in the present application can internally construct a model for determining the degree of atypicality of urine exfoliated cells, and use a deep learning algorithm to distinguish normal urine exfoliated cells, atypical urine exfoliated cells, malignant urine exfoliated cells and degenerate cells by calculating the cell nucleus-cytoplasm ratio, judging the regularity of nuclear membrane morphology, judging the fineness of chromatin, judging the prominence of nucleoli and judging the depth of nuclear staining. The identified atypical urine exfoliated cells and malignant urine exfoliated cells are highlighted as atypical cells, and corresponding classification result prompt labels are provided, such as atypical urine exfoliated cells and malignant urine exfoliated cells, to assist doctors in quickly locating the area where suspected diseased cells are located.The user interaction module 15 in the present application can be a data analysis software based on a graphical user interface, which provides intuitive user operation and result display for users to view and review the processing results of the atypical cell prompt module, and provides a user-defined analysis and analysis result filling module, allowing users to modify cell classification and issue final analysis results according to their subjective will.

[0030] As one of the preferred implementations, see Figure 1 The urine exfoliated cytology analysis system 10 provided in the present application also includes a data storage module 16, which is respectively connected to the information acquisition platform 11, the image processing module 13 and the atypical cell prompt module 14. The data storage module 16 is used to store the basic information of the owner of the urine exfoliated cytology slide, the whole slide image and the image processing results of the image processing module 13.

[0031] In addition, the data storage module 16 in the present application can also be connected to the user interaction module 15 to store the analysis results filled in by the user.

[0032] Furthermore, the present application also provides a method for analyzing urine exfoliated cytology, such as Figure 2 As shown, the method comprises the following steps:

[0033] Step S210, providing a basic information filling interface for the user to fill in the basic information of the owner of the urine exfoliated cytology slide, and generating an exclusive QR code for the urine exfoliated cytology slide;

[0034] Step S220, automatically planning a scanning path according to the size and shape of the urine exfoliated cytology slide with the exclusive QR code, scanning the urine exfoliated cytology slide based on the scanning path, and seamlessly splicing the multiple local cell images obtained by scanning into a complete full slide image;

[0035] Step S230, automatically locating, identifying and classifying cells in the whole slide image using an image detection algorithm;

[0036] Step S240, using a deep learning algorithm to calculate the relevant morphological parameters of the urine exfoliated cells identified by the image processing module, distinguishing normal urine exfoliated cells, atypical urine exfoliated cells, malignant urine exfoliated cells and degenerated cells based on the morphological parameters, highlighting atypical urine exfoliated cells and malignant urine exfoliated cells as atypical cells, and providing corresponding classification result prompt labels; the relevant morphological parameters include the size of the nucleus-cytoplasm ratio, the regularity of the nuclear membrane morphology, the fineness of the chromatin, the prominence of the nucleolus and the depth of the nuclear staining;

[0037] Step S250, providing a user interaction interface for the user to view and review the processing results of the atypical cell prompt module, and for the user to fill in the analysis results.

[0038] In the prior art, urine exfoliated cytology examination relies on experienced cytology experts to observe urine exfoliated cytology slides under a microscope to analyze the morphological changes of urine exfoliated cells in urine, and then issue a final diagnosis result based on subjective judgment and accumulated experience. However, cognitive differences among different cytology experts may lead to low consistency in urine exfoliated cytology analysis results, and manual observation and analysis are time-consuming, resulting in low efficiency of urine exfoliated cytology analysis in the prior art.

[0039] In order to solve the above problems, the present application provides a urine exfoliated cytology analysis system and a urine exfoliated cytology analysis method, including an information collection platform, an image scanning platform, an image processing module, an atypical cell prompting module and a user interaction module; the information collection platform is used to provide a basic information filling interface for users to fill in the basic information of the owner of the urine exfoliated cytology slide and generate an exclusive QR code for the urine exfoliated cytology slide; the image scanning platform is used to automatically plan a scanning path according to the size and shape of the urine exfoliated cytology slide with the exclusive QR code posted, scan the urine exfoliated cytology slide based on the scanning path, and seamlessly splice the multiple local cell images obtained by scanning into a complete full slide image; the image processing module uses an image detection algorithm to scan the full slide The cells in the film image are automatically located, identified and classified; the atypical cell prompt module uses a deep learning algorithm to calculate the relevant morphological parameters of the urine exfoliated cells identified by the image processing module, distinguishes normal urine exfoliated cells, atypical urine exfoliated cells, malignant urine exfoliated cells and degenerated cells based on the morphological parameters, and highlights atypical urine exfoliated cells and malignant urine exfoliated cells as atypical cells, and provides corresponding classification result prompt labels; the relevant morphological parameters include the size of the cell nucleus-cytoplasm ratio, the regularity of the nuclear membrane morphology, the fineness of the chromatin, the obviousness of the nucleolus and the depth of the nuclear staining; the user interaction module is used to provide a user interaction interface for users to view and review the processing results of the atypical cell prompt module, and for users to fill in the analysis results. This application introduces artificial intelligence technology to convert traditional urine exfoliated cytology physical slides into digital slides, simplify the process of manual microscopy, abandon the subjectivity and experience dependence of manual film reading and the limitations of traditional methods, promote the consistency of urine exfoliated cytology analysis results, and improve the speed, accuracy and sensitivity of urine exfoliated cytology analysis, thereby effectively improving the efficiency of urine exfoliated cytology analysis.

[0040] It should be understood that the specific embodiments described herein are only used to explain the application, rather than to limit it. Based on the embodiments provided in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the protection scope of this application.

[0041] Obviously, the drawings are only some examples or embodiments of the present application. For ordinary technicians in the field, the present application can also be applied to other similar situations based on these drawings without creative work. In addition, it is understandable that although the work done in this development process may be complicated and lengthy, for ordinary technicians in the field, certain changes in design, manufacturing or production based on the technical content disclosed in this application are only conventional technical means and should not be regarded as insufficient content disclosed in this application.

[0042] The term "embodiment" in this application refers to a specific feature, structure or characteristic described in conjunction with the embodiment that can be included in at least one embodiment of the present application. The appearance of this phrase in various locations in the specification does not necessarily mean the same embodiment, nor does it mean that it is mutually exclusive with other embodiments and is independent or optional. It is clearly or implicitly understood by those of ordinary skill in the art that the embodiments described in this application can be combined with other embodiments without conflict.

[0043] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of patent protection. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the scope of protection of the present application. Therefore, the scope of protection of the present application shall be subject to the attached claims.

Claims

1. A urine exfoliated cytology analysis system, characterized in that: It includes an information acquisition platform, an image scanning platform, an image processing module, an atypical cell prompting module and a user interaction module; The information collection platform is used to provide a basic information filling interface for users to fill in the basic information of the owner of the urine exfoliated cytology slide and generate an exclusive QR code for the urine exfoliated cytology slide; The image scanning platform is used to automatically plan a scanning path according to the size and shape of the urine exfoliated cytology slide with the exclusive QR code posted, scan the urine exfoliated cytology slide based on the scanning path, and seamlessly splice multiple local cell images obtained by scanning into a complete full slide image; The image processing module automatically locates, identifies and classifies cells in the whole slide image using an image detection algorithm; The atypical cell prompting module calculates the relevant morphological parameters of the urine exfoliated cells identified by the image processing module using a deep learning algorithm, distinguishes normal urine exfoliated cells, atypical urine exfoliated cells, malignant urine exfoliated cells and degenerated cells based on the morphological parameters, and highlights atypical urine exfoliated cells and malignant urine exfoliated cells as atypical cells, and provides corresponding classification result prompt labels; the relevant morphological parameters include the size of the cell nucleus-cytoplasm ratio, the regularity of the nuclear membrane morphology, the fineness of the chromatin, the obviousness of the nucleolus and the depth of the cell nuclear staining; The user interaction module is used to provide a user interaction interface for users to view and review the processing results of the atypical cell prompt module and for users to fill in the analysis results.

2. The urine exfoliated cytology analysis system according to claim 1, characterized in that: It also includes a data storage module, which is respectively connected to the information acquisition platform, the image processing module and the atypical cell prompt module, and is used to store basic information of the owner of the urine exfoliated cytology slide, the whole slide image and the image processing result recognized by the image processing module.

3. The urine exfoliated cytology analysis system according to claim 1, characterized in that: The basic information of the owner of the urine exfoliated cytology slide includes ID, name, age and gender.

4. A method for urine exfoliated cytology analysis, characterized in that: The method comprises the following steps: Providing a basic information filling interface for the user to fill in the basic information of the owner of the urine exfoliated cytology slide, and generating an exclusive QR code for the urine exfoliated cytology slide; Automatically planning a scanning path according to the size and shape of the urine exfoliated cytology slide with the exclusive QR code posted, scanning the urine exfoliated cytology slide based on the scanning path, and seamlessly splicing multiple local cell images obtained by scanning into a complete full slide image; Automatically locating, identifying and classifying cells in the whole slide image using an image detection algorithm; The deep learning algorithm is used to calculate the relevant morphological parameters of the urine exfoliated cells identified by the image processing module, and normal urine exfoliated cells, atypical urine exfoliated cells, malignant urine exfoliated cells and degenerate cells are distinguished based on the morphological parameters, and atypical urine exfoliated cells and malignant urine exfoliated cells are highlighted as atypical cells, and corresponding classification result prompt labels are provided; the relevant morphological parameters include the size of the cell nucleus-cytoplasm ratio, the regularity of the nuclear membrane morphology, the fineness of the chromatin, the prominence of the nucleolus and the depth of the cell nuclear staining; A user interaction interface is provided for users to view and review the processing results of the atypical cell prompt module and for users to fill in the analysis results.

Images