AI evaluation system for judging risk degree of pulmonary nodules

Abstract

The invention discloses an AI evaluation system for judging the risk degree of pulmonary nodules, and belongs to the technical field of medical treatment. The system mainly comprises an input module, a statistics module and a notification module. The input module comprises a patient input module, a hospital input module and a preprocessing module, a negative keyword library and a positive keyword library are arranged in the preprocessing module, and the preprocessing module is used for performing keyword comparison on an examination report; the keyword extraction module is used for extracting corresponding keywords in the negative keyword library and the positive keyword library in the examination report, and the statistical module is used for counting the number of the positive keywords and judging the pulmonary nodule risk degree according to the number of the positive keywords. And the notification module is internally provided with symptom description and risk description corresponding to each keyword in the negative keyword library and the positive keyword library. According to the AI evaluation system for judging the risk degree of the pulmonary nodules, the effect of preliminarily judging the risk degree of the pulmonary nodules is achieved.

Description

Technical Field

[0001] The present invention relates to the field of medical technology, and more specifically, to an AI evaluation system for determining the risk of pulmonary nodules. Background Art

[0002] The rapid development of artificial intelligence (AI) technology is reshaping the medical field. Through technologies such as deep learning, machine learning, and natural language processing, AI can efficiently process and analyze massive amounts of medical data, thereby achieving more accurate diagnosis and treatment. The combination of AI and medicine has not only improved the quality of medical services, but also greatly optimized the allocation of medical resources. In the future, with the continuous advancement of AI technology, medicine will enter a new era of greater intelligence, efficiency, and personalization.

[0003] With the popularization of low-dose spiral CT (LDCT) screening technology, the detection rate of small lung nodules has increased significantly. Research data show that the detection rate of LDCT in lung cancer screening can reach 20%-50%. However, about 95% of these detected lung nodules are benign lesions. Despite this, many patients still experience excessive anxiety and panic after discovering lung nodules. This not only affects the patient's mental health, but also increases the burden on the medical system. Therefore, how to effectively distinguish between benign and malignant nodules and provide timely guidance has become an urgent problem to be solved.

[0004] How to use advanced technology to self-diagnose the risk of lung nodules and alleviate the problems of difficulty in seeing a doctor and making appointments has become one of the challenges that modern medicine urgently needs to solve.

[0005] Therefore, it is necessary to provide an AI assessment system for judging the risk of lung nodules to solve the above problems. Summary of the invention

[0006] Based on the above-mentioned problems existing in the prior art, the purpose of the embodiments of the present application is to provide an AI assessment system for patients to self-judge the risk of lung nodules, so as to achieve the effect of preliminarily judging the risk of lung nodules.

[0007] The technical solution adopted by the present application to solve its technical problem is: an AI assessment system for determining the risk of pulmonary nodules, including an input module, a statistical module and a notification module;

[0008] The input module includes a patient input module, a hospital input module and a pre-processing module. The patient input module and the hospital input module are respectively used to allow patients and hospitals to upload their own examination reports to the pre-processing module. The pre-processing module is internally provided with a negative keyword library and a positive keyword library. The pre-processing module is used to perform keyword comparison on the examination report, extract the size of the lung nodules in the examination report, and the corresponding keywords in the negative keyword library and the positive keyword library. The statistical module is used to capture keywords and evaluate the risk of nodules according to the keywords and the size of the nodules. The notification module is provided with symptom descriptions and risk descriptions corresponding to each keyword in the negative keyword library and the positive keyword library.

[0009] Furthermore, the contents of the negative keyword library include: symmetrical chest, clear lung texture, centered trachea, unobstructed bronchial lumen (opening), no enlarged lymph nodes in the hilum / mediastinum, pleura (no thickening / smoothness), no pleural effusion, tiny nodules (less than 5 mm), a small amount of chronic (inflammation / inflammatory disease), calcification foci, proliferation foci, and no active lesions.

[0010] Furthermore, the contents of the positive keyword library include: high-risk nodules (greater than or equal to 5 mm), uneven density (less uniform); uneven density; inhomogeneity, partially solid nodules / subsolid nodules, solid components, masses; soft tissue masses; soft tissue shadows, unclear boundaries, inhomogeneity, burrs, lobulation, pleural indentation / pleural traction, bronchial occlusion, small vacuoles; vesicular sign, enlarged lymph nodes / enlarged lymph nodes / slightly larger lymph nodes, obstructive, mGGN; mGGO, air bronchial sign, bronchovascular bundles, atelectasis, cavities, irregularities, pure ground glass nodules, ground glass nodules / mixed ground glass nodules, blood vessels passing through, enhancement visible (mild / mild to moderate / obvious), pleural effusion.

[0011] Furthermore, the preprocessing module adopts the architecture of the GPT model, builds a basic large language model based on massive corpus, and collects relevant medical data as an aid.

[0012] Further, the following working steps are included:

[0013] S1. Send the inspection report to the input module;

[0014] S2, the pre-processing module extracts the keywords in the inspection report;

[0015] S3, statistical module to capture keywords;

[0016] S4, the statistical module determines the risk of lung nodules based on the keywords and the size of the lung nodules;

[0017] S5. Transmit the lung nodule risk, symptom description and risk description to the patient through the notification module.

[0018] Furthermore, in step S4, when the size of a small lung nodule is smaller than 5 mm, it is low risk regardless of whether there are keywords or not; when the size of a small lung nodule is 5-8 mm, if a positive keyword is found, it is judged as high risk, and if there is no positive keyword, it is low risk; when the small lung nodule is greater than or equal to 8 mm and there are only negative keywords, it is judged as low risk, and if a positive keyword is found or no keyword is found, it is judged as high risk.

[0019] Furthermore, the notification module network is connected to an external map software. In step S5, when the risk of lung nodules is medium risk or high risk, the evaluation results, symptom description and risk description are transmitted to the patient, and the address of a hospital near the patient is attached.

[0020] The beneficial effects of the present invention are:

[0021] By applying the system to a simple and easy-to-use mini-program, patients can upload their own examination reports for preliminary screening and provide timely follow-up guidance and suggestions, which will significantly alleviate patients' anxiety, reduce unnecessary panic and waiting time, reduce doctors' workload, and optimize the allocation of medical resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings constituting a part of the present invention are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the accompanying drawings:

[0023] Figure 1 This is an overall schematic diagram of an AI assessment system for determining the risk of pulmonary nodules in this application;

[0024] Figure 2 This is a schematic diagram of the workflow of an AI assessment system for determining the risk of pulmonary nodules in this application;

[0025] Figure 3 This is a display diagram of the negative keyword library and the positive keyword library. DETAILED DESCRIPTION

[0026] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application may be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0027] It should be noted that, unless otherwise specified, all technical and scientific terms used in this application have the same meanings as commonly understood by ordinary technicians in the technical field to which this application belongs.

[0028] In the present invention, unless otherwise specified, the directions used, such as "up" and "down", usually refer to the directions shown in the drawings, or to the vertical, perpendicular or gravity directions; similarly, for ease of understanding and description, "left" and "right" usually refer to the left and right shown in the drawings; "inside" and "outside" refer to the inside and outside relative to the outline of each component itself, but the above-mentioned directions are not used to limit the present invention.

[0029] like Figure 1-3 As shown, the present application provides an AI assessment system for determining the risk of lung nodules, including an input module, a statistical module and a notification module.

[0030] The input module includes the patient input module, hospital input module and pre-processing module. The patient input module is for patients to use. Some patients manually input their own examination reports through the input module or take photos and upload them to the pre-processing module. The hospital input module is used to cooperate with the hospital. During the patient examination process, the hospital automatically transmits the patient's examination report to the pre-processing module.

[0031] The preprocessing module is internally provided with a negative keyword library and a positive keyword library.

[0032] The negative keyword library includes: symmetrical chest, clear lung texture, centered trachea, unobstructed bronchial lumen (opening), no enlarged lymph nodes in the hilum / mediastinum, pleura (no thickening / smoothness), no pleural effusion, tiny nodules (less than 5 mm), a few chronic (inflammation / inflammatory), calcification foci, proliferative foci, and no active lesions.

[0033] The contents of the positive keyword library include: high-risk nodules (greater than or equal to 5mm), uneven density (less uniform); uneven density; inhomogeneity, partially solid nodules / subsolid nodules, solid components, masses; soft tissue masses; soft tissue shadows, unclear boundaries, inhomogeneity, burrs, lobulation, pleural indentation / pleural traction, bronchial occlusion, small vacuoles; vesicular sign, enlarged lymph nodes / enlarged lymph nodes / slightly larger lymph nodes, obstructive, mGGN; mGGO, air bronchogram, bronchovascular bundle, atelectasis, cavitation, irregularity, pure ground glass nodules, ground glass nodules / mixed ground glass nodules, blood vessels passing through, enhancement visible (mild / mild to moderate / obvious), pleural effusion.

[0034] The preprocessing module adopts the architecture of the GPT model, builds a basic large language model based on massive corpus, and collects relevant medical data as an aid to conduct sufficient keyword comparison of the examination report.

[0035] The statistical module determines the risk of lung nodules based on keywords and the size of small lung nodules.

[0036] The notification module is provided with symptom descriptions and risk descriptions corresponding to each keyword in the negative keyword library and the positive keyword library, and the notification module network is connected to an external map software.

[0037] An AI assessment system for determining the risk of pulmonary nodules includes the following steps:

[0038] S1. Send the inspection report to the input module;

[0039] S2, the pre-processing module extracts the keywords in the inspection report;

[0040] S3, statistical module to capture keywords;

[0041] S4, the statistical module determines the risk of lung nodules based on the positive keywords and the size of the lung nodules;

[0042] S5. Transmit the lung nodule risk, symptom description and risk description to the patient through the notification module.

[0043] In step S4, when the size of a small lung nodule is smaller than 5 mm, it is low risk regardless of whether there are keywords or not; when the size of a small lung nodule is 5-8 mm, if a positive keyword is found, it is judged as high risk, and if there is no positive keyword, it is low risk; when the small lung nodule is greater than or equal to 8 mm and there are only negative keywords, it is judged as low risk, and if a positive keyword is found or no keyword is found, it is judged as high risk.

[0044] In step S5, when the risk of lung nodules is medium risk or high risk, the assessment results, symptom description and risk description are transmitted to the patient, and the address of a hospital near the patient is attached.

[0045] By applying the system to a simple and easy-to-use mini-program, preliminary screening of patients' examination reports and timely provision of follow-up guidance and suggestions will significantly alleviate patients' anxiety, reduce unnecessary panic and waiting time, reduce doctors' workload, and optimize the allocation of medical resources.

[0046] Obviously, the above-described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0047] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0048] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein.

[0049] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0050] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. An AI assessment system for determining the risk of pulmonary nodules, characterized by: Includes input module, statistics module and notification module; The input module includes a patient input module, a hospital input module and a preprocessing module. The patient input module and the hospital input module are respectively used to allow patients and hospitals to upload their own examination reports to the preprocessing module. The preprocessing module is provided with a negative keyword library and a positive keyword library. The preprocessing module is used to perform keyword comparison on the examination report, extract the size of the lung nodules in the examination report, and the corresponding keywords in the negative keyword library and the positive keyword library. The statistical module is used to capture keywords and evaluate the risk of nodules based on the keywords and the size of the nodules. The notification module is provided with symptom descriptions and risk descriptions corresponding to each keyword in the negative keyword library and the positive keyword library.

2. The AI ​​assessment system for determining the risk of pulmonary nodules according to claim 1, characterized in that: The contents of the negative keyword library include: symmetrical chest, clear lung texture, centered trachea, unobstructed bronchial lumen (opening), no enlarged lymph nodes in the hilum / mediastinum, pleura (no thickening / smoothness), no pleural effusion, tiny nodules (less than 5 mm), a small amount of chronic (inflammation / inflammatory disease), calcification foci, proliferation foci, and no active lesions.

3. The AI ​​assessment system for determining the risk of pulmonary nodules according to claim 1, characterized in that: The contents of the positive keyword library include: high-risk nodules (greater than or equal to 5mm), uneven density (less uniform); uneven density; inhomogeneity, partially solid nodules / subsolid nodules, solid components, masses; soft tissue masses; soft tissue shadows, unclear boundaries, inhomogeneity, burrs, lobulation, pleural indentation / pleural traction, bronchial occlusion, small vacuoles; vesicular sign, enlarged lymph nodes / enlarged lymph nodes / slightly larger lymph nodes, obstructive, mGGN; mGGO, air bronchogram, bronchovascular bundle, atelectasis, cavity, irregular, pure ground glass nodules, ground glass nodules / mixed ground glass nodules, blood vessels passing through, enhancement visible (mild / mild to moderate / obvious), pleural effusion.

4. The AI ​​assessment system for determining the risk of pulmonary nodules according to claim 1, characterized in that: The preprocessing module adopts the architecture of the GPT model, builds a basic large language model based on massive corpus, and collects relevant medical data as an aid.

5. The AI ​​assessment system for determining the risk of pulmonary nodules according to claim 1, characterized in that: The following steps are included: S1. Send the inspection report to the input module; S2, the pre-processing module extracts the keywords in the inspection report; S3, the statistical module counts the negative keywords and positive keywords in the keywords; S4, the statistical module determines the risk of lung nodules based on positive keywords and negative keywords, as well as the size of lung nodules; S5. Transmit the lung nodule risk, symptom description and risk description to the patient through the notification module.

6. The AI ​​assessment system for determining the risk of pulmonary nodules according to claim 5, characterized in that: In step S4, when the size of a small lung nodule is smaller than 5 mm, it is low risk regardless of whether there are keywords or not; when the size of a small lung nodule is 5-8 mm, if a positive keyword is found, it is judged as high risk, and if there is no positive keyword, it is low risk; when the small lung nodule is greater than or equal to 8 mm and there are only negative keywords, it is judged as low risk, and if a positive keyword is found or no keyword is found, it is judged as high risk.

7. The AI ​​assessment system for determining the risk of pulmonary nodules according to claim 5, characterized in that: The notification module network is connected to an external map software. In step S5, when the risk of lung nodules is high, the evaluation results, symptom description and risk description are transmitted to the patient, and the address of a hospital near the patient is attached.

Images