Method for constructing a database of extranodal lymphoma pathology

Abstract

This invention provides a method for constructing an extranodal lymphoma pathology database, comprising: Step 1: determining a list of lymphoma subtypes to be included in the database based on the classification criteria for tumors of the lymphatic and hematopoietic systems; Step 2: generating a lymphoma subtype data package by obtaining at least a preset number of target cases for each lymphoma subtype according to the lymphoma subtype query list, wherein the target cases contain various clinical information; Step 3: storing the lymphoma subtype data package to establish an extranodal lymphoma pathology database. This invention establishes a digital slide library for extranodal lymphoma pathology, allowing medical students to search digital pathology knowledge graphs, retrieve digital pathology images related to pathology teaching text content, and view images with detailed clinical information. The library also automatically displays the differences between normal images and images with detailed annotations of lesions, allowing students to highlight key points and save notes, facilitating their pathology learning and improving learning efficiency.

Description

Technical Field

[0001] This invention relates to the field of database construction technology, and in particular to a method for constructing an extranodal lymphoma pathology database. Background Technology

[0002] The pathological diagnosis of lymphohematopoietic system tumors is usually based on the observation of tissue structure and cell morphology, supplemented by necessary immunohistochemical staining. This can diagnose and classify most tumors. For cases that cannot be definitively diagnosed through immunophenotype, molecular biology techniques such as gene rearrangement, fluorescence in situ hybridization (FISH), and gene expression profiling are needed to assist in further analysis and evaluation to achieve a precise diagnosis. Currently, those who can independently issue diagnostic reports for lymphohematopoietic system tumors are usually senior pathologists who typically undergo more than ten years of standardized training and pass professional theoretical and practical examinations before they are qualified. At the same time, in recent years, with the continuous development of fine-needle aspiration and endoscopic techniques, the number of complete lymph node biopsy specimens submitted for examination has decreased, while the number of small specimens obtained by aspiration and small tissues obtained by endoscopic biopsy has gradually increased. This has further increased the difficulty of diagnosing lymphomas, which are already diverse in morphology and complex in immunophenotype. When pathologists cannot observe the full picture of the lesion and make a lymphoma classification diagnosis, misdiagnosis and missed diagnosis are inevitable.

[0003] Traditional pathology teaching methods require medical students to observe gross specimens and examine pathological slides under a microscope after completing theoretical lectures. For beginners, lack of experience often makes it difficult to quickly identify typical lesion areas, and a significant amount of time is spent repeatedly switching between different areas for comparison. Furthermore, there is a lack of a database suitable for learning extranodal lymphoma pathology. Therefore, this invention provides a method for constructing an extranodal lymphoma pathology database. Summary of the Invention

[0004] This invention provides a method for constructing an extranodal lymphoma pathology database, which establishes a digital slide library for extranodal lymphoma pathology. Medical students can search the digital pathology knowledge graph, retrieve digital pathology images related to the text content of pathology teaching, and the images are accompanied by detailed clinical information. The database can also automatically display the differences between normal images and images with detailed annotations of lesions. Students can highlight key points and save notes, which facilitates students' pathology learning and improves the efficiency of pathology learning.

[0005] This invention provides a method for constructing a pathological database of extranodal lymphoma, comprising:

[0006] Step 1: Based on the classification criteria for tumors of the lymphatic and hematopoietic systems, determine the list of lymphoma subtypes to be included in the database;

[0007] Step 2: Based on the lymphoma subtype query list, generate a lymphoma subtype data package by obtaining at least a preset number of target cases for each lymphoma subtype, where the target cases contain a variety of clinical information;

[0008] Step 3: Store the lymphoma subtype data packets to establish an extranodal lymphoma pathology database.

[0009] Preferably, in a method for constructing an extranodal lymphoma pathology database, step 1 includes:

[0010] Based on the classification criteria for tumors of the lymphatic and hematopoietic systems, the types of tumors included in extranodal lymphomas are obtained, and a list of proposed entries is generated.

[0011] Based on the pathological properties of the tumors included in the proposed list of names to be included, the proposed list of names to be included is classified to generate a first-level classification directory;

[0012] A secondary classification directory is generated based on the tumor subtypes contained in the primary classification directory;

[0013] Based on the primary and secondary classification directories, a list of lymphoma subtypes is generated.

[0014] Preferably, in a method for constructing an extranodal lymphoma pathology database, step 2 includes:

[0015] Based on the lymphoma subtype query list and preset entry rules, generate the criteria for proposed entry cases for each lymphoma subtype.

[0016] Based on the criteria for proposed inclusion in the database, prospective cases are screened to obtain at least a preset number of target cases. At the same time, multiple clinical information corresponding to each target case is obtained to generate a lymphoma subtype data package.

[0017] After adding a type label to the lymphoma subtype data packet, the lymphoma subtype data packet is sent to the data lymphoma subtype query list.

[0018] Preferably, in a method for constructing an extranodal lymphoma pathology database, preliminary cases are screened based on the criteria for inclusion in the database, including:

[0019] Based on the criteria for cases to be included in the database, the indicators to be screened and the parameter characteristics corresponding to each indicator to be screened are obtained, the corresponding first data identifier is generated, and a data comparison table is generated based on the first data identifier.

[0020] Based on the parameter characteristics, the candidate cases are identified, and with reference to the first data identifier, the corresponding second data identifier is added to the data in the candidate cases based on the identification results;

[0021] Obtain the second data identifier for each candidate case. Based on the data comparison table, determine whether the data type of each candidate case meets the standard. If it does, determine whether the candidate case data is complete. If the candidate case data is complete, determine that the candidate case is the target case.

[0022] If the condition does not meet the requirements, the candidate case is determined to be a non-target case.

[0023] Preferably, in a method for constructing an extranodal lymphoma pathology database, determining whether the preliminary case data is complete includes:

[0024] Based on the data comparison table, obtain the standard data corresponding to various data.

[0025] Based on the standard data, extract the first data performance feature and the first data description feature corresponding to each data type, and at the same time obtain the second data performance feature and the second data description feature contained in the preliminary case.

[0026] The first data performance feature and the second data performance feature are compared for the first time. When the first data performance feature and the second data performance feature are consistent, the first data description feature and the second data description feature are compared for the second time. When the first data description feature and the second data description feature are consistent, the preliminary case data is determined to be complete.

[0027] When the first data description feature and the second data description feature are consistent, the preliminary case data is determined to be incomplete.

[0028] Preferably, in a method for constructing an extranodal lymphoma pathology database, when the first data performance characteristics are inconsistent with the second data performance characteristics, problematic data is acquired, content recognition is performed on the problematic data, it is determined whether the problematic data is correctly expressed, and if so, it is determined that the problematic data performance is consistent, and data description comparison is performed.

[0029] Otherwise, the preliminary case data is deemed incomplete.

[0030] Preferably, in a method for constructing an extranodal lymphoma pathology database, step 3 includes:

[0031] Based on the criteria for cases to be included in the database, the types of data contained in the lymphoma subtype data package are determined, and a three-level classification directory is generated based on the data types.

[0032] The final lymphoma subtype query list is obtained by adjusting the lymphoma subtype query list according to the three-level classification directory.

[0033] Based on the final lymphoma subtype query list, lymphoma subtype data are stored to establish an extranodal lymphoma pathology database.

[0034] Preferably, in a method for constructing an extranodal lymphoma pathology database, lymphoma subtype data is stored based on the final lymphoma subtype query list to establish an extranodal lymphoma pathology database, including:

[0035] Based on the final lymphoma subtype query list, a storage hierarchical tree structure is generated;

[0036] The lymphoma subtype data packets sent to the lymphoma subtype query list are labeled. Based on the label identification results, it is determined to cache the lymphoma subtype data packets in the first buffer of the lymphoma subtype query list. The number of cases of the corresponding lymphoma subtype is counted according to the label identification results, and a case number is added to the lymphoma subtype data packets according to the count results.

[0037] When the number of cases of the corresponding lymphoma subtype reaches the threshold, all lymphoma subtype data packets corresponding to the corresponding lymphoma subtype are sent to the second buffer and the data packets are parsed to obtain multiple reference case data groups.

[0038] Read the reference case data group in the second buffer according to the case number, and allocate the different types of reference case data to the corresponding nodes in the storage hierarchy tree structure according to the data identifier carried by each reference case data in the reference case data group.

[0039] Once each node of the storage hierarchy tree structure is filled, the reference case data is stored according to the node association relationship of the storage hierarchy tree structure to establish an extranodal lymphoma pathology database.

[0040] Preferably, in a method for constructing an extranodal lymphoma pathology database, the process of storing reference case data according to the node association relationship of a hierarchical tree structure includes:

[0041] A key data display unit is established for each lymphoma subtype. Immunohistochemical staining results for each reference case are obtained. The immunohistochemical staining results are transcribed into text and stored together with the image results in the key data display unit.

[0042] Meanwhile, the key data display unit is also used to obtain the remaining key reference information of the physician's diagnosis, extract the diagnostic reference data in the reference case based on the remaining key reference information, and store the diagnostic reference data after text transcription.

[0043] Preferably, a method for constructing an extranodal lymphoma pathology database further includes:

[0044] Step 4: Real-time monitoring of candidate cases. When new candidate cases are found, execute steps 1-3 to update the extranodal lymphoma pathology database.

[0045] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings.

[0046] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0047] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0048] Figure 1 This is a flowchart illustrating a method for constructing an extranodal lymphoma pathology database according to an embodiment of the present invention;

[0049] Figure 2 This is a flowchart of step 1 of a method for constructing an extranodal lymphoma pathology database according to an embodiment of the present invention;

[0050] Figure 3 This is a flowchart of step 2 of a method for constructing an extranodal lymphoma pathology database in an embodiment of the present invention;

[0051] Figure 4 This is a flowchart of step 3 of a method for constructing an extranodal lymphoma pathology database in an embodiment of the present invention. Detailed Implementation

[0052] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0053] Example 1:

[0054] This invention provides a method for constructing a pathological database of extranodal lymphoma, such as... Figure 1 As shown, it includes:

[0055] Step 1: Based on the classification criteria for tumors of the lymphatic and hematopoietic systems, determine the list of lymphoma subtypes to be included in the database;

[0056] Step 2: Based on the lymphoma subtype query list, generate a lymphoma subtype data package by obtaining at least a preset number of target cases for each lymphoma subtype, where the target cases contain a variety of clinical information;

[0057] Step 3: Store the lymphoma subtype data packets to establish an extranodal lymphoma pathology database.

[0058] In this embodiment, the classification standard for tumors of the lymphatic and hematopoietic systems is the latest WHO classification of tumors of the lymphatic and hematopoietic tissues.

[0059] The extranodal lymphoma subtypes to be included in the database include: extranodal B-cell lymphoma and extranodal T- and NK-cell lymphoma.

[0060] Extranodal B-cell lymphomas include extranodal mucosa-associated marginal zone B-cell lymphoma, extranodal follicular lymphoma, primary cutaneous follicular centrifugal lymphoma, primary mediastinal large B-cell lymphoma, primary central nervous system large B-cell lymphoma, empyema-associated lymphoma, primary cutaneous diffuse large B-cell lymphoma, leg-type, plasmablastic lymphoma, primary exudative lymphoma, lymphomatoid granuloma, intravascular large B-cell lymphoma, plasmacytoma, diffuse testicular large B-cell lymphoma, hairy cell leukemia, splenic marginal zone lymphoma, diffuse splenic red pulp small B-cell lymphoma, and diffuse large B-cell lymphoma originating from the spleen.

[0061] Extranodal T and NK cell lymphomas mainly include breast transplant-associated anaplastic large cell lymphoma, extranodal NK / T cell lymphoma, nasal type, enteropathy T cell lymphoma, hepatosplenic T cell lymphoma, monomorphic enterotropic epithelial T cell lymphoma, subcutaneous panniculitis-like T cell lymphoma, primary cutaneous γ / δ T cell lymphoma, mycosis fungoides, Sezary syndrome, primary cutaneous anaplastic large cell lymphoma, lymphomatoid papulosis, and T-prolymphocytic leukemia involving lymph nodes or other tissues.

[0062] In this embodiment, the lymphoma subtype lookup list is a data table containing various extranodal lymphoma subtypes, generated according to the classification criteria for tumors of the lymphatic and hematopoietic systems.

[0063] In this embodiment, the target pathology refers to the preliminary cases that meet the criteria for inclusion in the database. The preliminary cases are representative and classic cases that have been pre-screened, and the number of preliminary cases for each extranodal lymphoma subtype is greater than the preset number.

[0064] In this embodiment, the target case includes a variety of clinical information, including gender, age, lymphoma location, B symptoms, imaging, pre-treatment blood routine, serum LDH and β2 microglobulin levels, FISH (fluorescence in situ hybridization), gene rearrangement, flow cytometry immunophenotyping, next-generation gene sequencing, chromosome karyotype analysis, clinical stage, IPI score, chemotherapy regimen, and post-operative management guidance.

[0065] In this embodiment, the lymphoma subtype data package refers to a data package constructed from the pathological digital slices corresponding to the target case and all its corresponding clinical information, wherein the pathological digital slices have undergone [further processing / processing].

[0066] The beneficial effects of the above technical solution are as follows: Based on the classification standard of lymphatic and hematopoietic system tumors, this invention determines the list of lymphoma subtypes to be included in the database. Based on the list, it generates a lymphoma subtype data package by obtaining at least a preset number of target cases for each lymphoma subtype, ensuring that a certain amount of data can be obtained for each subtype. Then, the data contained in the lymphoma subtype data package is managed and stored to establish an extranodal lymphoma pathology database. This ensures the comprehensiveness of the data in the database, making it more suitable for students' case study and facilitating their study of extranodal lymphoma pathology at any time, thus improving learning efficiency.

[0067] Example 2:

[0068] Based on Example 1, such as Figure 2 As shown, step 1 includes:

[0069] Step 101: Based on the classification criteria for tumors of the lymphatic and hematopoietic systems, obtain the types of tumors included in extranodal lymphoma and generate a list of proposed entries into the database;

[0070] Step 102: Based on the pathological properties of the tumors included in the proposed list of names to be included, classify the proposed list of names to be included and generate a first-level classification directory;

[0071] Step 103: Generate a secondary classification directory based on the tumor subtypes contained in the primary classification directory;

[0072] Step 104: Generate a lymphoma subtype query list based on the primary and secondary classification directories.

[0073] In this embodiment, the pathological nature includes two types: extranodal B-cell lymphoma and extranodal T and NK-cell lymphoma.

[0074] In this embodiment, the proposed database includes a list of all subtypes of extranodal lymphoma.

[0075] The beneficial effects of the above technical solution are as follows: Based on the classification standard of tumors of the lymphatic and hematopoietic systems, this invention obtains the types of tumors included in extranodal lymphoma, generates a list of proposed entries, classifies the proposed entries according to the pathological properties of the tumors included in the list, generates a primary classification directory, and generates a secondary classification directory based on the tumor subtypes included in the primary classification directory; based on the primary and secondary classification directories, a lymphoma subtype query list is generated to perform preliminary classification of extranodal lymphoma, which facilitates students' learning to quickly confirm the pathological properties and also facilitates students' rapid data response when searching for data.

[0076] Example 3:

[0077] Based on Example 1, such as Figure 3As shown, step 2 includes:

[0078] Step 201: Based on the lymphoma subtype query list and preset entry rules, generate the criteria for proposed entry cases for each lymphoma subtype;

[0079] Step 202: Based on the criteria for proposed cases to be included in the database, screen the preliminary cases to obtain at least a preset number of target cases, and at the same time obtain multiple clinical information corresponding to each target case to generate a lymphoma subtype data package;

[0080] Step 203: After adding a type tag to the lymphoma subtype data packet, send the lymphoma subtype data packet to the data lymphoma subtype query list.

[0081] In this embodiment, the preset entry rules refer to the pre-set requirements for the data of each case to be entered into the database. For example, each case requires 1-2 key diagnostic HE-stained slides, and the slides are required to be clearly stained, with obvious contrast, bright color, distinct layers, and no fading; the tissue membranes are thin, flat, without wrinkles or compression, without cracks, scratches or abrasions, and the coverslips are straight and without air bubbles.

[0082] In this embodiment, the criteria for cases to be included in the database refer to the inclusion criteria generated based on the preset inclusion rules and the lymphoma subtype query list. These criteria include the types of cases that can be included in the database and the various data included in each case.

[0083] In this embodiment, the type label refers to the label indicating the external nodal lymphoma subtype corresponding to the lymphoma subtype data packet.

[0084] The beneficial effects of the above technical solution are as follows: Based on a lymphoma subtype query list and preset entry rules, this invention generates proposed case criteria for each lymphoma subtype; based on these criteria, pre-selected cases are screened to obtain at least a preset number of target cases, ensuring that the entered cases meet teaching requirements and providing students with high-quality learning materials as much as possible. Simultaneously, multiple clinical information corresponding to each target case is obtained, generating a lymphoma subtype data package; after adding a type tag to the lymphoma subtype data package, it is sent to the data lymphoma subtype query list, facilitating rapid confirmation of the lymphoma subtype corresponding to the data package during subsequent data storage and improving data storage processing efficiency.

[0085] Example 4:

[0086] Based on Example 3, the preliminary cases are screened according to the proposed inclusion criteria, including:

[0087] Based on the criteria for the proposed cases to be included in the database, the indicators to be screened and the parameter features corresponding to each indicator to be screened are obtained, and the corresponding first data identifier is generated. Based on the first data identifier, a data comparison table is generated.

[0088] Based on the parameter characteristics, the candidate cases are identified, and with reference to the first data identifier, the corresponding second data identifier is added to the data in the candidate cases based on the identification results;

[0089] Obtain the second data identifier for each candidate case. Based on the data comparison table, determine whether the data type of each candidate case meets the standard. If it does, determine whether the candidate case data is complete. If the candidate case data is complete, determine that the candidate case is the target case.

[0090] If the condition does not meet the requirements, the candidate case is determined to be a non-target case.

[0091] In this embodiment, the screening indicators refer to the indicators used to screen the preliminary cases, including the evaluation indicators of pathological digital slides and the evaluation indicators corresponding to various data contained in the preliminary cases.

[0092] In this embodiment, parameter characteristics refer to the data characteristics of various data parameters entered into the database.

[0093] In this embodiment, the first data identifier refers to the data identifier corresponding to all the data contained in the target case that has been entered into the database. This identifier indicates the data name of various data.

[0094] In this embodiment, the data lookup table refers to a table generated based on the first data identifier for determining the data type, which contains the data names corresponding to all the data.

[0095] In this embodiment, the second data identifier refers to the data identifier added to the pre-case based on the first data identifier.

[0096] The beneficial effects of the above technical solution are as follows: Based on the proposed case inclusion criteria, the present invention obtains the screening indicators and the parameter features corresponding to each screening indicator, generates the corresponding first data identifier, and generates a data comparison table. Based on the parameter features, the proposed cases are identified. Referring to the first data identifier, the corresponding second data identifier is added to the data in the proposed cases based on the identification results. The second data identifier of each proposed case is obtained, ensuring the comprehensiveness of the data carried by the lesion image and providing students with a more comprehensive and complete learning case.

[0097] Example 5:

[0098] Based on Example 4, determining whether the preliminary case data is complete includes:

[0099] Based on the data comparison table, obtain the standard data corresponding to various data.

[0100] Based on the standard data, extract the first data performance feature and the first data description feature corresponding to each data type, and at the same time obtain the second data performance feature and the second data description feature contained in the preliminary case.

[0101] The first data performance feature and the second data performance feature are compared for the first time. When the first data performance feature and the second data performance feature are consistent, the first data description feature and the second data description feature are compared for the second time. When the first data description feature and the second data description feature are consistent, the preliminary case data is determined to be complete.

[0102] When the first data description feature and the second data description feature are consistent, the preliminary case data is determined to be incomplete.

[0103] In this embodiment, the first data representation feature refers to the characteristics of different data representation forms of standard data, which may be text representation or image representation, or may include both representation forms at the same time.

[0104] The second data presentation characteristic refers to the presentation format of the different data contained in the preliminary case, which may be textual, image-based, or a combination of both.

[0105] In this embodiment, the first data description feature refers to the data feature of the data described in text in the standard data; the second data description feature refers to the data feature of the data described in text in the preliminary case.

[0106] The beneficial effects of the above technical solution are as follows: Based on a data comparison table, this invention determines whether the data types of each preliminary case meet the standards, quickly completes the integrity check of the data types, and then judges the integrity of the preliminary case data to ensure the integrity of the data entering the database and guarantee the data quality of each case entering the database, so that every case provided to students is more comprehensive and complete.

[0107] Example 6:

[0108] Based on Example 5, when the first data performance feature and the second data performance feature are inconsistent, problem data is obtained, content recognition is performed on the problem data, and it is determined whether the problem data is correctly expressed. If the problem data is correctly expressed, a data description comparison is performed.

[0109] Otherwise, the preliminary case data is deemed incomplete.

[0110] In this embodiment, problematic data refers to data whose representation is inconsistent with standard data.

[0111] In this embodiment, "correct expression" means that the data in the form of an image is converted into text form, or the data that contains both text and image forms is expressed only in text form.

[0112] When data in the form of images is converted into text, when comparing data descriptions, alternative data performance features of the non-important data are obtained, and the alternative data performance features are compared with second data performance features.

[0113] Among them, the alternative data performance characteristics refer to the corresponding textual representations of the data description features in the entered cases that allow the data in the image representation form to be converted into textual form.

[0114] The beneficial effects of the above technical solution are as follows: When the first data performance characteristics and the second data performance characteristics are inconsistent, the present invention obtains the problematic data, performs content recognition on the problematic data, avoids judgment errors caused by changes in the data performance form, ensures that the database can obtain target cases more comprehensively, and provides students with more learning reference materials that meet teaching requirements.

[0115] Example 7:

[0116] Based on Example 3, step 3, as follows: Figure 4 As shown, it includes:

[0117] Step 301: Based on the criteria for cases to be included in the database, determine the types of data contained in the lymphoma subtype data package, and generate a three-level classification directory based on the data types;

[0118] Step 302: Adjust the lymphoma subtype query list according to the three-level classification directory to obtain the final lymphoma subtype query list;

[0119] Step 303: Store the lymphoma subtype data based on the final lymphoma subtype query list and establish an extranodal lymphoma pathology database.

[0120] In this embodiment, the three-level classification directory refers to the name of the data type corresponding to the clinical information contained in each lymphoma subtype, which makes it convenient for students to view clinical information in a targeted manner when using the database described in this invention for data query.

[0121] In this embodiment, the final lymphoma subtype query list refers to the lymphoma subtype query list with a third-level directory added under the original second-level classification directory.

[0122] The beneficial effects of the above technical solution are as follows: Based on the criteria for cases to be included in the database, this invention determines the data types contained in the lymphoma subtype data package; based on these data types, a three-level classification directory is generated; and the lymphoma subtype query list is adjusted according to the three-level classification directory to obtain the final lymphoma subtype query list. Based on the final lymphoma subtype query list, the lymphoma subtype data is stored, establishing an extranodal lymphoma pathology database. This facilitates students in accessing targeted clinical information when using the database described in this invention for data queries, enabling students to tailor their learning to their specific needs.

[0123] Example 8:

[0124] Based on Example 7, lymphoma subtype data is stored based on the final lymphoma subtype query list to establish an extranodal lymphoma pathology database, including:

[0125] Based on the final lymphoma subtype query list, a storage hierarchical tree structure is generated;

[0126] The lymphoma subtype data packets sent to the lymphoma subtype query list are labeled. Based on the label identification results, it is determined to cache the lymphoma subtype data packets in the first buffer of the lymphoma subtype query list. The number of cases of the corresponding lymphoma subtype is counted according to the label identification results, and a case number is added to the lymphoma subtype data packets according to the count results.

[0127] When the number of cases of the corresponding lymphoma subtype reaches the threshold, all lymphoma subtype data packets corresponding to the corresponding lymphoma subtype are sent to the second buffer and the data packets are parsed to obtain multiple reference case data groups.

[0128] Read the reference case data group in the second buffer according to the case number, and allocate the different types of reference case data to the corresponding nodes in the storage hierarchy tree structure according to the data identifier carried by each reference case data in the reference case data group.

[0129] Once each node of the storage hierarchy tree structure is filled, the reference case data is stored according to the node association relationship of the storage hierarchy tree structure to establish an extranodal lymphoma pathology database.

[0130] In this embodiment, the storage hierarchical tree structure is generated based on the final lymphoma subtype query list to create a convenient storage hierarchical tree structure.

[0131] In this embodiment, the first buffer refers to the storage area for primary caching of lymphoma subtype data packets, where lymphoma subtype data of the same subtype are stored in the same sub-area.

[0132] In this embodiment, the second buffer refers to the storage area where all data packets corresponding to lymphoma subtypes that have reached a threshold number in the first buffer are parsed, and the reference case data refers to the data obtained after parsing the lymphoma subtype data packets.

[0133] In this embodiment, the case number refers to the number added according to the order in which lymphoma subtype data packets of the same subtype enter the first buffer, so as to facilitate orderly reading of data in the second buffer.

[0134] In this embodiment, the reference case data cluster refers to the data cluster obtained by parsing the lymphoma subtype data packet, and one lymphoma subtype data packet corresponds to one data cluster; the reference case data refers to the data in the reference case data cluster.

[0135] The beneficial effects of the above technical solution are as follows: Based on the final lymphoma subtype query list, this invention generates a hierarchical tree structure for convenient and orderly data storage, while also facilitating data retrieval during student learning, thus improving the learning experience. The invention performs tag identification on lymphoma subtype data packets sent to the lymphoma subtype query list. Based on the tag identification results, it determines to cache the lymphoma subtype data packets in the first buffer of the lymphoma subtype query list, and counts the number of cases for the corresponding lymphoma subtype according to the tag identification results, adding case serial numbers to the lymphoma subtype data packets according to the counting results. When the number of cases for the corresponding lymphoma subtype reaches a threshold, the corresponding lymphoma subtype... All lymphoma subtype data packets corresponding to the type are sent to the second buffer and parsed to obtain multiple reference case data groups. The reference case data groups in the second buffer are read according to the case number. Based on the data identifier carried by each reference case data in the reference case data group, the reference case data of different types are allocated to the nodes corresponding to the storage hierarchy tree structure. In the process of storing and classifying the data received from the lymphoma subtype query list, lymphoma subtype data packets of the same subtype are processed centrally. This not only ensures effective data processing but also improves the efficiency of data filling to nodes and ensures the accuracy of data storage location, providing students with accurate classified data for learning.

[0136] Example 9:

[0137] Based on Example 8, the process of storing reference case data according to the node association relationship of the storage hierarchy tree structure includes:

[0138] A key data display unit is established for each lymphoma subtype. Immunohistochemical staining results for each reference case are obtained. The immunohistochemical staining results are transcribed into text and stored together with the image results in the key data display unit.

[0139] Meanwhile, the key data display unit is also used to obtain the remaining key reference information of the physician's diagnosis, extract the diagnostic reference data in the reference case based on the remaining key reference information, and store the diagnostic reference data after text transcription.

[0140] In this embodiment, the remaining reference key information refers to other reference key information besides the immunohistochemical staining results.

[0141] In this embodiment, the key data display unit refers to the unit that highlights the pathological digital slide images. When students search for cases of relevant lymphoma subtypes, the content in the key data display unit is preferably displayed, and the corresponding normal images of the pathological digital slides automatically pop up, facilitating comparison and improving the efficiency of pathology learning. At the same time, students can view the accompanying clinical information while the pathological digital slides are displayed.

[0142] The beneficial effects of the above technical solution are as follows: During the process of storing reference case data according to the node association relationship of the storage hierarchy tree structure, the reference key information of the physician's diagnosis is transcribed into text, so that the pathological diagnosis results can be displayed more intuitively, which is convenient for students to learn. The key data display unit is set up to directly provide students with lesion images of the cases for querying, and automatically pops up the normal images corresponding to the pathological digital slices, which is convenient for students to compare and improve the efficiency of pathology learning.

[0143] Example 10:

[0144] Based on Example 3, a method for constructing an extranodal lymphoma pathology database further includes:

[0145] Step 4: Real-time monitoring of candidate cases. When new candidate cases are found, execute steps 1-3 to update the extranodal lymphoma pathology database.

[0146] The beneficial effects of the above technical solution are as follows: The present invention performs real-time detection of pre-existing cases. When a new pre-existing case is found, steps 1-3 are executed to complete the data update of the extranodal lymphoma pathology database, thereby realizing the autonomous updating of the database.

[0147] Example 11:

[0148] Based on Example 10, a method for constructing an extranodal lymphoma pathology database includes step 4:

[0149] Identify the pathological subtypes corresponding to new prospective cases and calculate the data weights of these pathological subtypes in the extranodal lymphoma pathology database:

[0150]

[0151] Where, ω qThis indicates the data weight of the pathological subtype corresponding to the new candidate case in the current extranodal lymphoma pathology database; q represents the code of the pathological subtype corresponding to the new candidate case, where the codes for pathological subtypes in the extranodal lymphoma pathology database are 1, 2, ..., K; N q This indicates the number of cases in the current extranodal lymphoma pathology database that correspond to the pathological subtype of the new preset case; M represents the total number of cases in the current extranodal lymphoma pathology database; N I This represents the number of cases of the I-th pathological subtype stored in the current extranodal lymphoma pathology database, where I = 1, 2, ..., K;

[0152] When the data weight is less than or equal to the minimum threshold, execute steps 1-3 to update the data in the extranodal lymphoma pathology database.

[0153] Otherwise, obtain the access priority for the pathological subtype corresponding to the new pre-existing case:

[0154]

[0155] Where, γ q This indicates the access priority for the pathological subtype corresponding to a new candidate case; P represents the total number of visits to the extranodal lymphoma pathology database at the current stage; P q This represents the total number of visits at the current stage corresponding to the pathological subtype of the new preliminary case; β q The learning impact factor, with a value range of (0, 1], when β q When β = 1, the pathological subtype corresponding to the proposed case is the focus of learning at this stage. q The larger the value, the more important it is to learn about this pathological subtype at the current stage;

[0156] When the access priority is greater than the preset access priority, steps 1-3 are executed to update the data in the extranodal lymphoma pathology database.

[0157] Otherwise, proceed to steps 1-2 to determine whether the new candidate case meets the database storage requirements. If it does, obtain all stored reference cases corresponding to the pathological subtype of the new candidate case, delete the stored case with the fewest views, and proceed to step 3 to store the new candidate case in the extranodal lymphoma pathology database for data update.

[0158] If the conditions are not met, stop updating the extranodal lymphoma pathology database.

[0159] The beneficial effects of the above technical solution are as follows: Based on the pathological subtype corresponding to the new preparatory case, the present invention calculates the data weight of the pathological subtype in the extranodal lymphoma pathology database, determines whether the case storage of the pathological subtype corresponding to the new preparatory case is too small. If it is too small, the new preparatory case is directly processed and the database is updated to ensure that the pathological storage of various pathological subtypes in the extranodal lymphoma pathology database is maintained at a certain level, ensuring that students can complete the learning of each pathological subtype in the database. At the same time, when the case storage of the pathological subtype corresponding to the new preparatory case is large, the access priority of the pathological subtype corresponding to the new preparatory case is calculated to determine whether the pathological subtype corresponding to the new preparatory case is the focus of the student's current stage of learning. If so, the database is directly updated to ensure that the database can provide students with a sufficient number of reference cases that they currently need. Otherwise, it is necessary to delete the pathological subtype corresponding to the new preparatory case that students have viewed the least, i.e., the pathological cases with low browsing volume. The database is updated without adding memory pressure or running pressure to the database. The present invention autonomously completes the data update of the database while ensuring the quality of the new cases.

[0160] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for constructing a pathological database for extranodal lymphoma, characterized in that, include: Step 1: Based on the classification criteria for tumors of the lymphatic and hematopoietic systems, determine the list of lymphoma subtypes to be included in the database; Step 2: Based on the lymphoma subtype query list, generate a lymphoma subtype data package by obtaining at least a preset number of target cases for each lymphoma subtype, where the target cases contain a variety of clinical information; Step 3: Store the lymphoma subtype data packets to establish an extranodal lymphoma pathology database; Step 2 includes: Based on the lymphoma subtype query list and preset entry rules, generate the criteria for proposed entry cases for each lymphoma subtype. Based on the criteria for proposed inclusion in the database, prospective cases are screened to obtain at least a preset number of target cases. At the same time, multiple clinical information corresponding to each target case is obtained to generate a lymphoma subtype data package. After adding a type label to the lymphoma subtype data packet, the lymphoma subtype data packet is sent to the data lymphoma subtype query list; Step 4: Real-time monitoring of candidate cases. When new candidate cases are found, execute steps 1-3 to update the extranodal lymphoma pathology database. Step 4 includes: Identify the pathological subtypes corresponding to new prospective cases and calculate the data weights of these pathological subtypes in the extranodal lymphoma pathology database: Where, ω q This indicates the data weight of the pathological subtype corresponding to the new candidate case in the current extranodal lymphoma pathology database; q represents the code of the pathological subtype corresponding to the new candidate case, where the codes for pathological subtypes in the extranodal lymphoma pathology database are 1, 2, ..., K; N q This indicates the number of cases in the current extranodal lymphoma pathology database that correspond to the pathological subtype of the new preset case; M represents the total number of cases in the current extranodal lymphoma pathology database; N I This represents the number of cases of the I-th pathological subtype stored in the current extranodal lymphoma pathology database, where I = 1, 2, ..., K; When the data weight is less than or equal to the minimum threshold, execute steps 1-3 to update the data in the extranodal lymphoma pathology database. Otherwise, obtain the access priority for the pathological subtype corresponding to the new pre-existing case: Where, γ q This indicates the access priority for the pathological subtype corresponding to a new candidate case; P represents the total number of visits to the extranodal lymphoma pathology database at the current stage; P q This represents the total number of visits at the current stage corresponding to the pathological subtype of the new preliminary case; β q The learning impact factor, with a value range of (0, 1], when β q When β = 1, the pathological subtype corresponding to the proposed case is the focus of learning at this stage. q The larger the value, the more important it is to learn about this pathological subtype at the current stage; When the access priority is greater than the preset access priority, steps 1-3 are executed to update the data in the extranodal lymphoma pathology database. Otherwise, proceed to steps 1-2 to determine whether the new candidate case meets the database storage requirements. If it does, obtain all stored reference cases corresponding to the pathological subtype of the new candidate case, delete the stored case with the fewest views, and proceed to step 3 to store the new candidate case in the extranodal lymphoma pathology database for data update. If the conditions are not met, stop updating the extranodal lymphoma pathology database.

2. The method for constructing an extranodal lymphoma pathology database according to claim 1, characterized in that, Step 1 includes: Based on the classification criteria for tumors of the lymphatic and hematopoietic systems, the types of tumors included in extranodal lymphomas are obtained, and a list of proposed entries is generated. Based on the pathological properties of the tumors included in the proposed list of names to be included, the proposed list of names to be included is classified to generate a first-level classification directory; A secondary classification directory is generated based on the tumor subtypes contained in the primary classification directory; Based on the primary and secondary classification directories, a list of lymphoma subtypes is generated.

3. The method for constructing an extranodal lymphoma pathology database according to claim 1, characterized in that, Based on the aforementioned criteria for inclusion in the database, prospective cases are screened, including: Based on the criteria for cases to be included in the database, the indicators to be screened and the parameter characteristics corresponding to each indicator to be screened are obtained, the corresponding first data identifier is generated, and a data comparison table is generated based on the first data identifier. Based on the parameter characteristics, the candidate cases are identified, and with reference to the first data identifier, the corresponding second data identifier is added to the data in the candidate cases based on the identification results; Obtain the second data identifier for each candidate case. Based on the data comparison table, determine whether the data type of each candidate case meets the standard. If it does, determine whether the candidate case data is complete. If the candidate case data is complete, determine that the candidate case is the target case. If the condition does not meet the requirements, the candidate case is determined to be a non-target case.

4. The method for constructing an extranodal lymphoma pathology database according to claim 3, characterized in that, Determining whether the preliminary case data is complete includes: Based on the data comparison table, obtain the standard data corresponding to various data. Based on the standard data, extract the first data performance feature and the first data description feature corresponding to each data type, and at the same time obtain the second data performance feature and the second data description feature contained in the preliminary case. The first data performance feature and the second data performance feature are compared for the first time. When the first data performance feature and the second data performance feature are consistent, the first data description feature and the second data description feature are compared for the second time. When the first data description feature and the second data description feature are consistent, the preliminary case data is determined to be complete. When the first data description feature and the second data description feature are consistent, the preliminary case data is determined to be incomplete.

5. The method for constructing an extranodal lymphoma pathology database according to claim 4, characterized in that: When the first data performance characteristics are inconsistent with the second data performance characteristics, problem data is obtained, content recognition is performed on the problem data, and it is determined whether the problem data is correctly expressed. If so, it is determined that the problem data performance is consistent, and data description comparison is performed. Otherwise, the preliminary case data is deemed incomplete.

6. The method for constructing an extranodal lymphoma pathology database according to claim 1, characterized in that, Step 3 includes: Based on the criteria for cases to be included in the database, the types of data contained in the lymphoma subtype data package are determined, and a three-level classification directory is generated based on the data types. The final lymphoma subtype query list is obtained by adjusting the lymphoma subtype query list according to the three-level classification directory. Based on the final lymphoma subtype query list, lymphoma subtype data are stored to establish an extranodal lymphoma pathology database.

7. The method for constructing an extranodal lymphoma pathology database according to claim 6, characterized in that, Based on the final lymphoma subtype query list, lymphoma subtype data are stored to establish an extranodal lymphoma pathology database, including: Based on the final lymphoma subtype query list, a storage hierarchical tree structure is generated; The lymphoma subtype data packets sent to the lymphoma subtype query list are labeled. Based on the label identification results, it is determined to cache the lymphoma subtype data packets in the first buffer of the lymphoma subtype query list. The number of cases of the corresponding lymphoma subtype is counted according to the label identification results. Case serial numbers are added to the lymphoma subtype data packets according to the counting results. When the number of cases of the corresponding lymphoma subtype reaches the threshold, all lymphoma subtype data packets corresponding to the corresponding lymphoma subtype are sent to the second buffer and the data packets are parsed to obtain multiple reference case data groups. Read the reference case data group in the second buffer according to the case number, and allocate the different types of reference case data to the corresponding nodes in the storage hierarchy tree structure according to the data identifier carried by each reference case data in the reference case data group. Once each node of the storage hierarchy tree structure is filled, the reference case data is stored according to the node association relationship of the storage hierarchy tree structure to establish an extranodal lymphoma pathology database.

8. The method for constructing an extranodal lymphoma pathology database according to claim 7, characterized in that, The process of storing reference case data according to the node relationships in the storage hierarchy tree structure includes: A key data display unit is established for each lymphoma subtype. Immunohistochemical staining results for each reference case are obtained. The immunohistochemical staining results are transcribed into text and stored together with the image results in the key data display unit. Meanwhile, the key data display unit is also used to obtain the remaining key reference information of the physician's diagnosis, extract the diagnostic reference data in the reference case based on the remaining key reference information, and store the diagnostic reference data after text transcription.

Images