Thyroid cell pathological image auxiliary analysis system, method and equipment

Through the combination of automatic detection and analysis of thyroid cell pathological image assisted analysis system and manual input by pathologists, the problem of the time spent and decision-making power of thyroid cell pathological image analysis in the prior art is solved, the diagnosis efficiency and accuracy are improved, and the reduction of Unnecessary thyroidectomy and disease progression risk.

CN118942645APending Publication Date: 2024-11-12JIANGSU SIMCERE MEDICAL DEVICE CO LTD +2
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411057021.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-02
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

The existing thyroid cell pathological image analysis methods consume a lot of time and energy, or the pathologist's decision-making power over pathological image analysis is not included in it, which limits the promotion of technology in clinical applications.

Method used

Provide a thyroid cell pathological image assisted analysis system, including a patient database and an analysis platform. Through the analysis platform, it connects to the patient database to realize automatic detection and analysis of thyroid cell pathological images, outputs malignant probability, benign and malignant diagnosis and suspicious malignant areas, assists Pathologists can efficiently read the film to diagnose and allow pathologists to manually input diagnostic results based on their own experience.

Benefits of technology

It improves the diagnostic efficiency and accuracy of diagnostic results of pathologists, reduces unnecessary thyroidectomy, and reduces the risk of disease progression caused by missed thyroid cancer.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118942645A_ABST
    Figure CN118942645A_ABST
Patent Text Reader

Abstract

The invention provides a thyroid cell pathological image auxiliary analysis system, method and equipment. An analysis platform is connected with a patient database, patient information can be obtained based on the analysis platform, automatic detection and analysis of a thyroid cell pathological image of a target patient can be achieved, whether the pathological image is qualified or not is judged firstly, and the malignancy probability, benign and malignant diagnosis and suspicious malignant areas are output for a pathologist to refer to; meanwhile, a cell pathology image and image blocks obtained by dividing the cell pathology image can be displayed for a pathologist to check, the pathologist is assisted in efficiently reading and diagnosing, and the diagnosis efficiency of the pathologist is improved; in addition, a pathologist can manually input pathologic description and pathologic diagnosis according to own experience judgment, so that the accuracy of a diagnosis result is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to a thyroid cell pathology image-assisted analysis system, method and device, and belongs to the field of computer technology. Background Art

[0002] Thyroid cancer is the malignant tumor with the fastest growing incidence in the world in the past three decades, and the incidence of thyroid cancer in my country is also showing a rapid upward trend. Behind thyroid cancer is an even larger population of thyroid nodules. Under high-resolution ultrasound detection, the detection rate of thyroid nodules in the population is as high as 68%, of which only about 7-10% are thyroid cancer. Not all thyroid nodules have the potential to worsen. Benign and malignant thyroid nodules have completely different genetic backgrounds, and benign nodules do not increase the risk of thyroid cancer. Excessive thyroidectomy not only increases the medical burden, but also greatly increases the risk of surgical complications such as parathyroid injury, recurrent laryngeal nerve paralysis, and bleeding. Therefore, in the face of a large base of thyroid nodules, how to improve the accuracy of differential diagnosis of benign and malignant thyroid nodules to avoid unnecessary thyroidectomy and reduce disease progression caused by missed diagnosis of thyroid cancer is of great clinical significance.

[0003] Thyroid fine needle aspiration biopsy (FNA) is the "gold standard" for preoperative diagnosis of benign and malignant thyroid nodules recommended by both domestic and international thyroid cancer diagnosis and treatment guidelines. However, due to the limitations of thyroid FNA, the number of thyroid follicular epithelial cells in a thyroid cell pathology image is usually small and scattered. Pathologists spend a lot of time and energy in the process of searching for follicular epithelial cell clusters, which is a labor-intensive task. In addition, in recent years, some teams have used artificial intelligence technology to develop fully automatic analysis models for thyroid cell pathology images. However, these analysis models do not include the pathologist's decision-making power in pathology image analysis, which limits the promotion of these technologies in clinical application. Summary of the invention

[0004] The present application provides a thyroid cell pathology image auxiliary analysis system, method and equipment to solve the problems of existing thyroid cell pathology image analysis methods, such as consuming a lot of time and energy or not incorporating the pathologist's decision-making power on pathology image analysis.

[0005] In a first aspect, an embodiment of the present application provides a thyroid cell pathology image-assisted analysis system, which includes a patient database and an analysis platform;

[0006] The patient database is used to store patient information;

[0007] The analysis platform is used to analyze and process the thyroid cell pathology images of the patients selected by the pathologist to obtain the diagnosis results of the selected patients, and the diagnosis results include the judgment results of whether the pathology images are qualified, the probability of malignancy, the benign and malignant diagnosis and the suspected malignant area;

[0008] The analysis platform includes an interactive interface, which includes a first display area, a second display area and an input area; the first display area is used to display thumbnails of all thyroid cell pathology images of the selected patient, the malignancy probability at the patient level, the benign and malignant diagnosis at the patient level, and the panoramic pathology image of the thyroid cell pathology image selected by the pathologist, the judgment result of whether the panoramic pathology image is qualified and the corresponding malignancy probability; the second display area is used to display thumbnails of a preset number of image blocks with the highest malignancy probability in the thyroid cell pathology image selected by the pathologist, as well as the panoramic image and the corresponding malignancy probability of the image block selected by the pathologist; the input area is used for the pathologist to input the pathology description and pathology diagnosis result.

[0009] Based on the above system, optionally, the patient information includes medical number, name, gender, age, specimen source, specimen type, sending hospital, sending department, sending doctor, sending date and cytopathology image.

[0010] Based on the above system, optionally, the first display area can zoom in or out the currently displayed panoramic pathology image according to the operation of the pathologist.

[0011] Based on the above system, optionally, the second display area can enlarge or reduce the currently selected image block according to the operation of the pathologist.

[0012] Based on the above system, optionally, the first display area can also display the position of the image block selected by the pathologist in the second display area in the corresponding panoramic pathology image.

[0013] In a second aspect, an embodiment of the present application further provides a thyroid cell pathology image-assisted analysis method, which is applied to the analysis platform of the thyroid cell pathology image-assisted analysis system as described in any one of the first aspects, and the method comprises:

[0014] Determining the patient information of the patient to be diagnosed selected by the pathologist, and acquiring all thyroid cell pathology images of the patient from a patient database based on the patient information;

[0015] Displaying thumbnails of all thyroid cell pathology images of the selected patient in the first display area, judging whether the pathology images are qualified based on all thyroid cell pathology images of the selected patient, and calculating and outputting the patient-level malignancy probability and the patient-level benign and malignant diagnosis;

[0016] Determine the thyroid cell pathology image selected by the pathologist, and display a panoramic pathology image of the selected thyroid cell pathology image, a judgment result of whether the panoramic pathology image is qualified and a corresponding malignancy probability in the first display area, and display thumbnails of a preset number of image blocks with a high malignancy probability in the selected thyroid cell pathology image in the second display area;

[0017] Determine the image block selected by the pathologist, and display a panoramic view of the selected image block and a corresponding malignancy probability in the second display area;

[0018] Obtaining pathological descriptions and pathological diagnosis results input by pathologists;

[0019] A diagnosis report is generated based on the pathological description and the pathological diagnosis result.

[0020] In a third aspect, an embodiment of the present application further provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor calls and executes the computer program, the thyroid cell pathology image-assisted analysis method described in the second aspect is implemented.

[0021] The above technical solution provided by this application has at least the following beneficial effects:

[0022] In the thyroid cell pathology image auxiliary analysis system, method and equipment provided by the present application, by connecting the analysis platform with the patient database, the patient information can be obtained based on the analysis platform and automatic detection and analysis of the thyroid cell pathology images of the target patient can be realized, and the malignancy probability, benign and malignant diagnosis and suspected malignant area can be output for the reference of the pathologist. At the same time, the cell pathology image and the image blocks obtained by dividing the cell pathology image can be displayed for the pathologist to view, so as to assist the pathologist in reading the film efficiently and improve the diagnostic efficiency of the pathologist. In addition, the pathologist can also manually input the pathology description and pathology diagnosis based on his own experience and judgment to improve the accuracy of the diagnosis results. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification are used to explain the principles of the present application. In addition, these drawings and text descriptions are not intended to limit the scope of the concept of the present application in any way, but to illustrate the concept of the present application for those skilled in the art by referring to specific embodiments.

[0024] Figure 1 A schematic diagram of the architecture of a thyroid cell pathology image-assisted analysis system provided in one embodiment of the present application;

[0025] Figure 2 A schematic diagram of a display interface of an analysis platform provided in one embodiment of the present application;

[0026] Figure 3 A schematic diagram of a flow chart of a thyroid cell pathology image-assisted analysis method provided in one embodiment of the present application;

[0027] Figure 4 A schematic diagram of the structure of an electronic device provided for one embodiment of the present application. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical solutions and advantages of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in combination with the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0029] As mentioned in the background technology section, after obtaining thyroid cell pathology images based on FNA technology, if pathologists manually search for useful cells (thyroid follicular epithelial cells), it will take a lot of time and effort. If a fully automatic analysis model is used for diagnosis, the decision-making power of pathologists on pathology image analysis cannot be included, thus limiting the application and promotion of these technologies in clinical practice.

[0030] In order to solve the above problems, the present application provides a thyroid cell pathology image auxiliary analysis system, method and equipment, wherein, by connecting the analysis platform with the patient database, the patient information can be obtained based on the analysis platform and the automatic detection and analysis of the thyroid cell pathology image of the target patient can be realized, and the pathology image can be judged whether it is qualified, and the malignancy probability, benign and malignant diagnosis and suspected malignant area can be output for reference by the pathologist, so as to assist the pathologist in efficient film reading and diagnosis and improve the diagnostic efficiency of the pathologist; in addition, the analysis platform can also display the cell pathology image and the image blocks obtained by dividing the cell pathology image for the pathologist to view, so that the pathologist can make a diagnosis based on his own experience, and manually input the pathology description and pathology diagnosis results to improve the accuracy of the diagnosis results. The specific implementation scheme is described non-restrictively below through several examples or embodiments.

[0031] First, some embodiments of the present application provide a thyroid cell pathology image-assisted analysis system. Based on this system, pathologists can be assisted to quickly locate the thyroid follicular epithelial cell cluster area, reduce the time it takes for pathologists to find cell clusters, and provide information such as benign and malignant probabilities for reference by pathologists, thereby improving the diagnostic efficiency of pathologists.

[0032] Reference Figure 1 , Figure 1Schematic diagram of the architecture of a thyroid cell pathology image-assisted analysis system provided in an embodiment of the present application. Figure 1 As shown, the thyroid cell pathology image-assisted analysis system of this embodiment includes a patient database and an analysis platform.

[0033] Among them, the patient database is used to store patient information.

[0034] In some embodiments, the patient information includes medical number, name, gender, age, specimen source, specimen type, hospital where the specimen was sent for examination, department where the specimen was sent for examination, doctor where the specimen was sent for examination, date of the specimen sent for examination, and cytopathological image. The cytopathological image is an image obtained by scanning the cytopathological smear using a digital pathological section scanner. The cytopathological smear can be prepared by obtaining thyroid cells using FNA technology.

[0035] The analysis platform is used to analyze and process the thyroid cell pathology images of patients selected by the pathologist to obtain the diagnosis results of the selected patients. The diagnosis results include the judgment result of whether the pathology image is qualified, the probability of malignancy, benign and malignant diagnosis and suspected malignant areas.

[0036] The analysis platform includes an interactive interface, which includes a first display area, a second display area and an input area.

[0037] The first display area is used to display thumbnails of all thyroid cell pathology images of the selected patient, patient-level malignancy probability, patient-level benign and malignant diagnosis, and panoramic pathology images of thyroid cell pathology images selected by the pathologist, the judgment results of whether the panoramic pathology images are qualified, and the corresponding malignancy probability.

[0038] Among them, the judgment result of whether the pathological image is qualified is to analyze each thyroid cell pathology image separately to confirm whether it is a qualified image that can be used for diagnosis. Specifically, if a thyroid cell pathology image contains enough useful cells (thyroid follicular epithelial cells), the corresponding judgment result is qualified. The patient-level malignancy probability refers to the malignancy probability obtained by the analysis platform based on a comprehensive analysis of all thyroid cell pathology images of the patient, and the patient-level benign and malignant diagnosis refers to the benign or malignant diagnosis result obtained by the analysis platform based on a comprehensive analysis of all thyroid cell pathology images of the patient. Accordingly, the pathologist can select one of the thumbnails of all thyroid cell pathology images to view its panoramic pathology image, and the first display area also displays the panoramic pathology image of the selected cell pathology image, as well as the judgment result and malignancy probability of the pathology image obtained by the analysis platform based only on the cell pathology image analysis. The above information can be used as a reference for pathologists to improve diagnostic efficiency.

[0039] The second display area is used to display thumbnails of a preset number of image blocks with the highest malignancy probabilities in the thyroid cell pathology image selected by the pathologist, as well as a panoramic view of the image blocks selected by the pathologist and the corresponding malignancy probabilities.

[0040] Among them, the image blocks are obtained by segmenting the complete cytopathology image, and each cytopathology image can be segmented into multiple image blocks. The analysis platform can analyze and process the information contained in each image block respectively, so as to obtain the malignancy probability corresponding to each image block. In addition, the analysis platform can screen a certain number of image blocks with high malignancy probabilities from all image blocks corresponding to the panoramic pathology image currently displayed in the first display area, and display thumbnails of these image blocks with high malignancy probabilities in the second display area. Accordingly, the pathologist can select one of the thumbnails of all image blocks with high malignancy probabilities to view its panoramic view, and the second display area will also display the malignancy probability obtained by the analysis platform based only on the analysis of the image block. The above information can be used as a reference for pathologists to improve diagnostic efficiency.

[0041] The input area is used by pathologists to input pathological descriptions and pathological diagnosis results. After viewing the diagnosis results and images displayed by the analysis platform as needed, pathologists can make analysis and judgments based on their own experience and input pathological descriptions and pathological diagnosis results in the input area, thereby combining clinical experience with the analysis results of the analysis platform to obtain more accurate diagnosis results.

[0042] It should be noted that the analysis platform can use existing neural network models or algorithms to perform image analysis and processing to obtain the corresponding malignancy probability and benign or malignant diagnosis results, or it can also develop or train corresponding algorithm models. This application does not impose any restrictions on this, as long as the required results can be obtained.

[0043] In some embodiments, the first display area can zoom in or out the currently displayed panoramic pathology image according to the pathologist's operation, so that the pathologist can conveniently view the details of certain areas of the panoramic pathology image of interest.

[0044] In some embodiments, the second display area can also enlarge or reduce the currently selected image block according to the pathologist's operation, so that the pathologist can conveniently view the details of certain image areas of the image block of interest.

[0045] In addition, in some embodiments, the first display area can also display the position of the image block selected by the pathologist in the second display area in the corresponding panoramic pathology image, so that the pathologist can review and browse the panoramic pathology image as needed.

[0046] Based on the above-mentioned thyroid cell pathology image auxiliary analysis system, by connecting the analysis platform with the patient database, the patient information can be obtained based on the analysis platform and automatic detection and analysis of the thyroid cell pathology images of the target patients can be realized, and the judgment results of whether the pathology images are qualified, the probability of malignancy, the benign and malignant diagnosis and the suspected malignant areas can be output for the reference of the pathologist. At the same time, the cell pathology images and the image blocks obtained by dividing the cell pathology images can be displayed for the pathologist to view, so as to assist the pathologist to read the films efficiently and improve the diagnostic efficiency of the pathologist. In addition, the pathologist can also manually input the pathology description and pathology diagnosis based on his own experience and judgment to improve the accuracy of the diagnosis results.

[0047] In order to make the above solution easier to understand, the analysis platform is further explained below in conjunction with the accompanying drawings and the user (pathologist) usage process.

[0048] First, a patient database is provided. The patient database is used to store patient information, including at least diagnosis number, name, gender, age, specimen source, specimen type, sending hospital, sending department, sending doctor, sending date and scanned cytopathology images. The patient database is connected to the analysis platform. Figure 2 A schematic diagram of the display interface of an analysis platform provided for one embodiment of the present application.

[0049] The user operation process is as follows:

[0050] Step 1: The pathologist opens the analysis platform, clicks the patient list button at the bottom, and selects a patient in the pop-up list (not shown).

[0051] Step 2: The pathologist clicks the detection and analysis button, and the analysis platform will display thumbnails of all thyroid cell pathology images of the selected patient in the first display area A1, and calculate and output the patient-level malignancy probability and the patient-level benign and malignant diagnosis based on all slices. The first display area A1 is located in the upper left part of the display interface. The top of the first display area A1 can display part of the patient information, such as name, age, gender, etc., for the pathologist to view; the left side of the first display area A1 displays slice thumbnails, and each slice (slice 1 to slice n) corresponds to a thyroid cell pathology image. Multiple slice images can be arranged from top to bottom in a certain order (such as according to the malignancy probability), and the patient-level malignancy probability and the patient-level benign and malignant diagnosis information are displayed below the slice thumbnails.

[0052] Step 3: Pathologists slice the slides Figure 1When a slice image is selected in the column, the analysis platform displays the panoramic pathology image of the selected slice in the first display area A1 (which can be enlarged and reduced), and determines whether the panoramic pathology image of the slice is qualified and calculates the probability of malignancy, which is displayed below the panoramic pathology image. At the same time, a preset number of thumbnails of image blocks with high malignant probabilities are displayed in the second display area A2. The panoramic pathology image of the selected slice can be enlarged and reduced. The image enlargement button is represented by a "+" symbol, and the image reduction button is represented by a "-" symbol. The second display area A2 is located on the right side of the first display area A1. The right part of the second display area A2 displays a preset number of thumbnails of image blocks with high malignant probabilities. These image blocks correspond to the panoramic pathology image currently displayed in the first display area A1.

[0053] Step 4: Pathologist’s thumbnail of the image block Figure 1 Select an image block in the column, and the analysis platform will present a panoramic view of the image block on the left side of the second display area A2 ( Figure 2 In the image block, "X" indicates the selected image block) and the probability of malignancy, and locates the position of the image block in the panoramic pathology image of the slice. The pathologist can review the panoramic pathology image as needed. The panoramic image of the selected image block can be enlarged and reduced. The image enlargement button is represented by a "+" symbol, and the image reduction button is represented by a "-" symbol.

[0054] Step 5: The pathologist inputs the pathological description and final pathological diagnosis in the input area A3 at the lower part of the display interface according to the malignancy probability and benign or malignant diagnosis detected and analyzed by the platform and his own judgment.

[0055] Step 6: The pathologist clicks the Save button and then clicks the Export Result button to export the final results.

[0056] Through the above scheme, the analysis platform can realize automatic detection and analysis of the patient's thyroid cell pathology images, output the probability of malignancy, benign and malignant diagnosis and suspected malignant image areas (i.e. image blocks with a high probability of malignancy) for reference by pathologists, and assist pathologists in efficient film reading and diagnosis. Pathologists can also manually input pathological descriptions and pathological diagnoses based on their own experience to improve the accuracy of diagnostic results.

[0057] In addition, an embodiment of the present application also provides a thyroid cell pathology image-assisted analysis method, which is applied to the analysis platform of the thyroid cell pathology image-assisted analysis system described in any of the above embodiments, that is, executed by the analysis platform.

[0058] like Figure 3 As shown, the thyroid cell pathology image-assisted analysis system of this embodiment includes the following steps:

[0059] Step S101: determining the patient information of the patient to be diagnosed selected by the pathologist, and acquiring all thyroid cell pathology images of the patient from the patient database based on the patient information.

[0060] Specifically, the pathologist can open the analysis platform, click the patient list button, and select a patient in the pop-up list. After selection, the analysis platform will automatically obtain all the patient's information from the patient database, including thyroid cell pathology images, etc.

[0061] Step S102: Display thumbnails of all thyroid cell pathology images of the selected patient in the first display area, and judge whether the selected pathology image is qualified based on all thyroid cell pathology images of the selected patient, and calculate and output the patient-level malignancy probability and the patient-level benign or malignant diagnosis.

[0062] Specifically, the pathologist can click the detection and analysis button on the display interface of the analysis platform. The analysis platform will automatically perform analysis and processing based on the built-in algorithm to obtain the patient-level malignancy probability and the patient-level benign and malignant diagnosis results for display, as well as display thumbnails of all thyroid cell pathology images of the selected patient.

[0063] Step S103: Determine the thyroid cell pathology image selected by the pathologist, and display a panoramic pathology image and a corresponding malignancy probability of the selected thyroid cell pathology image in the first display area, and display thumbnails of a preset number of image blocks with the highest malignancy probability in the selected thyroid cell pathology image in the second display area.

[0064] Specifically, the pathologist can Figure 1 Click on a slice image in the bar, and the analysis platform will automatically display the panoramic pathology image and the corresponding malignancy probability of the selected thyroid cell pathology image in the first display area, and at the same time, display the thumbnails of the preset number of image blocks with the highest malignancy probability in the selected thyroid cell pathology image in the second display area. If the pathologist does not select a thyroid cell pathology image, the panoramic pathology image of the first slice image can be displayed by default, or no panoramic pathology image can be displayed, which can be set as needed.

[0065] Step S104: determining the image block selected by the pathologist, and displaying the panoramic view of the selected image block and the corresponding malignancy probability in the second display area.

[0066] Specifically, the pathologist can Figure 1 Click to select a certain image block in the column, and the analysis platform will display the panoramic view of the selected image block and the corresponding malignancy probability in the second display area.

[0067] Step S105: Obtain the pathological description and pathological diagnosis result input by the pathologist.

[0068] Specifically, the pathologist can input the pathological description and final pathological diagnosis in the input area at the lower part of the display interface based on his own judgment according to the malignancy probability and benign or malignant diagnosis output by the platform analysis and after viewing each image or image block.

[0069] Step S106: Generate a diagnosis report based on the pathology description and the pathology diagnosis result.

[0070] Specifically, the analysis platform ultimately inputs a diagnostic report for download and review.

[0071] In some embodiments, optionally, after step S104, the method further includes: displaying the location of the image block selected by the pathologist in the panoramic pathology image displayed in the first display area, so that the doctor can review and browse the panoramic pathology image as needed.

[0072] Among them, regarding the specific implementation methods of each step of the above-mentioned thyroid cell pathology image-assisted analysis method, the parts that are not described in detail can refer to the corresponding contents in the aforementioned system embodiment and will not be repeated here.

[0073] Based on the above method, the automatic detection and analysis of the patient's thyroid cell pathology images can be realized, and the malignancy probability, benign and malignant diagnosis and suspected malignant image areas (i.e. image blocks with higher malignancy probability) can be output for reference by pathologists, assisting pathologists in efficient film reading and diagnosis. Pathologists can also manually input pathology descriptions and pathology diagnoses based on their own experience and judgment to improve the accuracy of diagnostic results.

[0074] In addition, some embodiments of the present application also provide an electronic device, such as Figure 4 As shown, the electronic device includes a memory 41 and a processor 42, wherein the memory 41 stores a computer program, and when the processor 42 calls and executes the computer program, the thyroid cell pathology image-assisted analysis method as described in any of the above embodiments is implemented.

[0075] The electronic device may be a notebook computer or a desktop computer.

[0076] It can be understood that the same or similar parts of the above embodiments can be referenced to each other, and the contents not described in detail in some embodiments can refer to the same or similar contents in other embodiments.

[0077] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention belong.

[0078] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0079] A person of ordinary skill in the art may understand that all or part of the steps of the method for implementing the above-mentioned embodiment may be completed by instructing the relevant hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one of the steps of the method embodiment or a combination thereof.

[0080] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium. The above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0081] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0082] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A thyroid cell pathology image-assisted analysis system, characterized in that: Includes patient database and analytics platform; The patient database is used to store patient information; The analysis platform is used to analyze and process the thyroid cell pathology images of the patients selected by the pathologist to obtain the diagnosis results of the selected patients, and the diagnosis results include the judgment results of whether the pathology images are qualified, the probability of malignancy, the benign and malignant diagnosis and the suspected malignant area; The analysis platform includes an interactive interface, which includes a first display area, a second display area and an input area; the first display area is used to display thumbnails of all thyroid cell pathology images of the selected patient, the malignancy probability at the patient level, the benign and malignant diagnosis at the patient level, and the panoramic pathology image of the thyroid cell pathology image selected by the pathologist, the judgment result of whether the panoramic pathology image is qualified and the corresponding malignancy probability; the second display area is used to display thumbnails of a preset number of image blocks with the highest malignancy probability in the thyroid cell pathology image selected by the pathologist, as well as the panoramic image and the corresponding malignancy probability of the image block selected by the pathologist; the input area is used for the pathologist to input the pathology description and pathology diagnosis result.

2. The system according to claim 1, characterized in that The patient information includes medical number, name, gender, age, specimen source, specimen type, sending hospital, sending department, sending doctor, sending date and cytopathology image.

3. The system according to claim 1, characterized in that The first display area can enlarge or reduce the currently displayed panoramic pathology image according to the operation of the pathologist.

4. The system according to claim 1, characterized in that The second display area can enlarge or reduce the currently selected image block according to the operation of the pathologist.

5. The system according to claim 1, characterized in that The first display area can also display the position of the image block selected by the pathologist in the second display area in the corresponding panoramic pathology image.

6. A method for assisting analysis of thyroid cell pathology images, characterized in that: The analysis platform applied to the thyroid cell pathology image-assisted analysis system according to any one of claims 1 to 5, the method comprising: Determining the patient information of the patient to be diagnosed selected by the pathologist, and acquiring all thyroid cell pathology images of the patient from a patient database based on the patient information; Displaying thumbnails of all thyroid cell pathology images of the selected patient in the first display area, judging whether the pathology images are qualified based on all thyroid cell pathology images of the selected patient, and calculating and outputting the patient-level malignancy probability and the patient-level benign and malignant diagnosis; Determine the thyroid cell pathology image selected by the pathologist, and display a panoramic pathology image of the selected thyroid cell pathology image, a judgment result of whether the panoramic pathology image is qualified and a corresponding malignancy probability in the first display area, and display thumbnails of a preset number of image blocks with a high malignancy probability in the selected thyroid cell pathology image in the second display area; Determine the image block selected by the pathologist, and display a panoramic view of the selected image block and a corresponding malignancy probability in the second display area; Obtaining pathological descriptions and pathological diagnosis results input by pathologists; A diagnosis report is generated based on the pathological description and the pathological diagnosis result.

7. The method according to claim 6, characterized in that After determining the image block selected by the pathologist and displaying the panoramic view of the selected image block and the corresponding malignancy probability in the second display area, the method further includes: In the panoramic pathological image displayed in the first display area, the position of the image block selected by the pathologist is displayed.

8. An electronic device, characterized in that: It comprises a memory and a processor, wherein the memory stores a computer program, and when the processor calls and executes the computer program, the thyroid cell pathology image-assisted analysis method as claimed in claim 6 or 7 is implemented.