CN111445996A - Medical information processing method, processing system and storage medium - Google Patents

Abstract

The disclosure relates to a medical information processing method, which includes obtaining first to third identification information based on AI identification of first medical information, second medical information and third medical information, wherein the first identification information includes a tumor primary focus condition, and the second identification information includes a regional lymph node affected condition; the third identification information includes a distant transfer condition; and outputting interpretation information according to the first identification information, the second identification information, the third identification information and the standard information. The medical information processing system is linked with the medical diagnosis service data system through a corresponding data interface; the method comprises the following steps: the AI identification module is used for obtaining identification information respectively containing different pathological information based on different medical information; and the analysis module is used for obtaining the interpretation information according to different identification information and standard information. Through the embodiments of the present disclosure, the intelligent inference of the corresponding diagnosis information can be realized, the working efficiency of the doctor can be improved, and the clinical data preparation cost can be reduced.

Description

Medical information processing method, processing system and storage medium

Technical Field

The present disclosure relates to the field of medical information technology, and in particular, to a medical information processing method, a medical information processing system, and a computer-readable storage medium.

Background

In the field of medical big data, the prior art has the problems of irregular writing of medical records and high data interpretation loss rate, and the key technology is used for helping doctors to extract diagnosis information such as TNM staging and the like, thereby being helpful for clinicians. In some scenarios, only the diagnostic information already mentioned in the case is extracted, the missing relevant information cannot be extracted, or only some relevant information is extracted to the physician without the process of intelligent inference.

Disclosure of Invention

The present disclosure is intended to provide a method, a system and a computer readable storage medium for processing medical information, which can intelligently infer corresponding diagnostic information, improve the working efficiency of doctors, and reduce the clinical data preparation cost.

According to one aspect of the present disclosure, there is provided a medical information processing method including:

obtaining first identification information based on AI identification of first medical information, wherein the first identification information comprises the condition of a tumor primary focus;

obtaining second identification information based on AI identification of second medical information, wherein the second identification information comprises regional lymph node involvement;

obtaining third identification information based on AI identification of third medical information, wherein the third identification information comprises a distant metastasis condition;

and outputting interpretation information according to the first identification information, the second identification information, the third identification information and the standard information.

In some embodiments, wherein the identifying based on AI of the first medical information comprises:

and extracting key text contents from the text expression, and identifying the key text contents through machine learning or deep learning.

In some embodiments, wherein the identifying based on AI of the first medical information comprises:

extracting primary focus from medical image, and identifying image parameter of primary focus through AI.

In some embodiments, wherein the identifying based on AI of the second medical information comprises:

when the text expression associated with the second medical information exists, extracting key text content from the existing text expression, and identifying the key text content through machine learning or deep learning;

when there is no text expression associated with the second medical information, the farthest lymph node is extracted in the medical image in combination with the primary lesion, and the image parameters of the lymph node are identified by the AI.

In some embodiments, wherein said extracting key text content from the existing text expressions comprises:

from the lymph node puncture pathology report, a lymph node puncture pathology report result was extracted based on N L P.

In some embodiments, wherein the identifying based on the AI of the third medical information comprises:

when the text expression associated with the third medical information exists, extracting key text contents from the existing text expression, and identifying the key text contents through machine learning or deep learning;

when there is no text expression associated with the third medical information, a lesion is extracted in the medical image, and a multiple and/or single occurrence of the lesion is identified by the AI.

In some embodiments, the first and second light sources, wherein,

extracting key text content from existing text presentation, including extracting text description content of the focus from diagnosis reports of other parts based on N L P;

the step of extracting the focus in the medical image comprises the step of extracting the focus from medical images of other parts, wherein the medical images of other parts comprise MRI images, CT images and nuclear medicine bone scanning images.

In some embodiments, wherein the outputting the interpretation information according to the first identification information, the second identification information, the third identification information, and the standard information includes:

and outputting interpretation information about the lung cancer by taking the TNM staging standard as standard information.

According to one of the schemes of the disclosure, a medical information processing system is provided and is linked with a medical diagnosis service data system through a corresponding data interface; wherein the processing system of the medical information comprises:

the AI identification module is configured to obtain different identification information based on different medical information, wherein the different identification information respectively comprises different pathological information;

and the analysis module is used for obtaining the interpretation information according to different identification information and standard information.

According to one aspect of the present disclosure, there is provided a computer-readable storage medium having stored thereon computer-executable instructions that, when executed by a processor, implement:

the method for processing medical information is described above.

The medical information processing method, the medical information processing system and the computer-readable storage medium according to various embodiments of the present disclosure obtain different identification information based on at least different medical information, where the different identification information includes different pathological information, and obtain interpretation information according to the different identification information and standard information. Through the technical scheme of each embodiment of the disclosure, an intelligent medical information processing process combining text and image picture analysis can be realized, for example, a TNM stage intelligent inference scheme, wherein key information is extracted from reports and image pictures by utilizing multi-mode data comprehensive treatment capability of a multi-service system and combining medical semantic accurate interpretation capability based on a knowledge graph, TNM stages are automatically inferred by using clinical TNM stage value-taking rules, so that the working efficiency of doctors can be greatly improved, and the cost is reduced.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure, as claimed.

Drawings

In the drawings, which are not necessarily drawn to scale, like reference numerals may designate like components in different views. Like reference numerals with letter suffixes or like reference numerals with different letter suffixes may represent different instances of like components. The drawings illustrate various embodiments generally, by way of example and not by way of limitation, and together with the description and claims, serve to explain the disclosed embodiments.

Fig. 1 shows a flowchart of a method for processing medical information according to an embodiment of the present disclosure;

fig. 2 shows an architecture diagram of a medical information processing system according to an embodiment of the present disclosure.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present disclosure more clear, the technical solutions of the embodiments of the present disclosure will be described below clearly and completely with reference to the accompanying drawings of the embodiments of the present disclosure. It is to be understood that the described embodiments are only a few embodiments of the present disclosure, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the described embodiments of the disclosure without any inventive step, are within the scope of protection of the disclosure.

Unless otherwise defined, technical or scientific terms used herein shall have the ordinary meaning as understood by one of ordinary skill in the art to which this disclosure belongs. The word "comprising" or "comprises", and the like, means that the element or item listed before the word covers the element or item listed after the word and its equivalents, but does not exclude other elements or items.

To maintain the following description of the embodiments of the present disclosure clear and concise, a detailed description of known functions and known components have been omitted from the present disclosure.

The technical scheme of the embodiment of the disclosure relates to medical information processing, including analysis, processing and interpretation of focus information, tumor information and the like. For example, the treatment method in the tumor field needs to follow the international or national standard, and the most important reference in the guideline is TNM for the treatment of non-small cell lung cancer patients, such as in the National Comprehensive Cancer Network (NCCN), if the treatment plan in stage I/II is the first choice of operation, the appropriate drug treatment plan for gene detection is considered after stage IV. The TNM information is particularly important in the field of medical big data, the problems that medical record writing is not standard and the TNM deletion rate is high exist at present due to historical reasons, and the key technology is used for helping doctors to extract the TNM stage information, so that great help is provided for clinicians.

Lung cancer is generally classified into two major categories according to its pathological type, namely non-small cell lung cancer (NSC L C) and small cell lung cancer (SC L C), non-small cell lung cancer includes squamous cell carcinoma, adenocarcinoma, and large cell undifferentiated carcinoma, which account for 80% -85% of all lung cancers, and their specific classification does not affect the choice of therapy, small cell lung cancer accounts for 15% -20% of all lung cancers, also clinically known as oat cell carcinoma, small cell undifferentiated carcinoma, and poorly differentiated neuroendocrine carcinoma.

TNM is known as Tumor/Node/Metastasis, wherein:

t (Tumor) refers to the condition of a primary tumor focus, and is sequentially represented by T1-T4 with increasing tumor volume and increasing affected range of adjacent tissues, T0: no evidence of the presence of a primary tumor, Tis: no dissemination of an early tumor to adjacent tissues, T1-4: size and/or range of primary tumor for lung cancer, Tx: primary tumor cannot be evaluated, or sputum, bronchoscopic flushing fluid finds cancer cells but no visible tumor is available with imaging or bronchoscopy T0: no evidence of a primary tumor Tis: in situ T1: a tumor of very large diameter ≦ 3 cm, surrounded by lung or pleural lining, subtenon tumor has no involvement of the bronchioles above (i.e., no involvement of the bronchiole and main bronchi), T2: a tumor size or range conforming to any of ① tumor of very large diameter >3, ② cm and main bronchi, but no involvement of the same distance between the pleural space of the septum, 2, pleural space, and pleural space, no involvement of the lung, no invasion of the lung septum spacing between the septum, lung and lung septum, no invasion of the lung septum, lung septum spacing between the lung and lung wall, no invasion of the lung 638, lung septum, lung ductal notch, no invasion of the lung 638, lung septum, lung, no invasion of the lung or pleural effusion of the lung transverse pleural effusion, no invasion of the lung 6326, no invasion of the lung or pleural effusion, no invasion of the lung transverse pleural effusion of the same lung or pleural space (no invasion of the lung 638, no invasion of the lung or pleural space < 7, 4, no invasion of the lung ductus notch, no invasion of the lung 638, no invasion of the lung, no obstruction of the lung or lung, no obstruction of the lung.

N (node) indicates the affected condition of regional lymph node (regional lymph node), and when the lymph node is not affected, it is represented by N0, and with the increase of the affected degree and range of lymph node, it is represented by N1-N3: NX regional lymph node status was not assessed; n0 No regional lymph node involvement (no tumor found in lymph nodes); n1 that only a few nearby lymph nodes were affected; n2 cases between the conditions of N1 and N3 (not applicable to all tumors); n3 distant and/or more lymph nodes were affected (not applicable to all tumors). For lung cancer, it can be considered that: nx: it is impossible to judge whether the regional lymph glands are metastasized. N0: there was no regional lymph gland metastasis. N1: metastasis to ipsilateral paratracheal and/or ipsilateral pulmonary portal lymph glands and primary tumors directly invade the intrapulmonary lymph glands. N2: transferred to the ipsilateral mediastinal diaphragm and/or the infracarinal lymph glands. N3: transferred to the contralateral mediastinal diaphragm, the contralateral supraglottic lymph gland, and the ipsilateral or contralateral scalene muscle or supraclavicular ganglion.

M (Metastasis) refers to distant metastases (usually blood-tract metastases), with those without distant metastases denoted M0 and those with distant metastases denoted M1. For lung cancer, it can be considered that: mx: the presence or absence of distant metastasis cannot be estimated. M0: there was no distant metastasis. M1: there was distant metastasis (M1 for metastatic nodules ipsilateral to the primary tumor, but on different lobes).

As one aspect, as shown in fig. 1, an embodiment of the present disclosure provides a method for processing medical information, including:

s101: obtaining first identification information based on AI identification of first medical information, wherein the first identification information comprises the condition of a tumor primary focus;

s102: obtaining second identification information based on AI identification of second medical information, wherein the second identification information comprises regional lymph node involvement;

s103: obtaining third identification information based on AI identification of third medical information, wherein the third identification information comprises a distant metastasis condition;

s104: and outputting interpretation information according to the first identification information, the second identification information, the third identification information and the standard information.

The method aims to identify corresponding medical information through AI, can identify text content recording the medical information, and extracts corresponding content by utilizing AI technology according to pathological reports and other reports forming words and sentence records. Taking a lung examination report as an example, the lung examination report may be "tumor size", "whether leaf bronchus is involved", "whether pleura is involved", "whether diaphragm is involved", "lymph node metastasis part", "distant metastasis part", and the like, and the text expression contains key contents required by TNM stage, the contents in the text may be extracted by using a machine learning or deep learning method, the T stage, the N stage, and the M stage are determined according to the extracted actual contents, and then corresponding pathological TNM stage interpretation information is obtained according to corresponding stage standards.

As some aspects, the obtaining of the first identification information based on AI identification of the first medical information according to the embodiment of the present disclosure, where the first identification information includes a tumor origin, may be: the identification based on AI of the first medical information comprises:

and extracting key text contents from the text expression, and identifying the key text contents through machine learning or deep learning.

For text records, such as medical records, pathological document reports, etc., the AI extraction technology of the present embodiment comprehensively determines a tumor site, that is, a site of a focus of chief complaint, may employ a processing method of Natural language processing (N L P: Natural L Natural language processing), and through deep learning algorithms such as automatic word segmentation, syntactic analysis, part of speech tagging, etc., obtains relevant text contents including, but not limited to, "tumor size", "location, size, volume, density, symptom, doubling time of a tumor mass of a primary focus", and identifies and generates identification information including the condition of the tumor primary focus, including "tumor size", "whether a bronchus is involved", "whether a pleura is involved", "whether a is involved", and "diaphragm is involved".

In some other aspects, the obtaining of the first identification information based on AI identification of the first medical information according to the embodiments of the present disclosure, where the first identification information includes a tumor origin, may be: the identification based on AI of the first medical information comprises:

extracting primary focus from medical image, and identifying image parameter of primary focus through AI.

For CT chest images, embodiments of the present disclosure may employ a fully quantitative analysis and intelligent diagnosis of pulmonary CT with an intelligent 4D imaging system. Specifically, CT breast images can be acquired, and image parameters of tumor mass of the primary lesion, including the position, size, volume, density, signs, doubling time, etc., can be accurately identified by image AI extraction techniques, and then identified and identification information including the condition of the tumor primary lesion can be generated. Including "tumor size", "whether or not it affects the leaf bronchus", "whether or not it affects the pleura", "whether or not it affects the diaphragm", and so on.

Further, the obtaining of the second identification information based on AI identification of the second medical information according to the embodiment of the present disclosure may be: the identification based on AI of the second medical information includes:

when the text expression associated with the second medical information exists, extracting key text content from the existing text expression, and identifying the key text content through machine learning or deep learning;

when there is no text expression associated with the second medical information, the farthest lymph node is extracted in the medical image in combination with the primary lesion, and the image parameters of the lymph node are identified by the AI.

Specifically, when there is a corresponding text expression, the AI extraction technique of this embodiment determines the corresponding expression content comprehensively for the text records, such as medical records, pathological document reports, etc., and may use an N L P processing method to obtain corresponding identification information through deep learning algorithms such as automatic word segmentation, syntactic analysis, part-of-speech tagging, etc. for example, if there is a lymph node puncture pathological report, the N L P technique may be used to extract the pathological report result and make intelligent inference according to the extraction result.

As a further implementation manner, the obtaining of the third identification information based on AI identification of the third medical information according to the embodiment of the present disclosure, where the third identification information includes the far-end transfer case, may be: the identifying based on the AI of the third medical information includes:

when the text expression associated with the third medical information exists, extracting key text contents from the existing text expression, and identifying the key text contents through machine learning or deep learning;

when there is no text expression associated with the third medical information, a lesion is extracted in the medical image, and a multiple and/or single occurrence of the lesion is identified by the AI.

Specifically, the key text content is extracted from the existing text expression, the text description content of the focus is extracted from the diagnosis report of other parts based on N L P, the focus is extracted from the medical image of other parts, and the medical image of other parts comprises an MRI image, a CT image and a nuclear medicine bone scanning image.

When corresponding text expressions exist, the AI extraction technology of the embodiment comprehensively determines corresponding expression contents from text records of other objective examination reports of a patient, such as medical records, pathological document reports and the like, and can adopt an N L P processing mode to obtain corresponding identification information through deep learning algorithms such as automatic word segmentation, syntactic analysis, part of speech tagging and the like.

By combining the embodiments of the present disclosure with the actual application scenarios of TNM staging interpretation and lung cancer inference, the following is described by way of specific embodiments:

the TNM stage interface in the specific product can comprise 3 parts, namely T stage, N stage and M stage, wherein for a follow-up examination mode, namely lung CT, which is commonly used by lung cancer patients, an intelligent 4D image system is adopted to carry out comprehensive quantitative analysis and intelligent diagnosis on the lung CT, and for other objective examination reports of the patients, such as MRI, CT at other parts, pathological reports, nuclear medicine bone scanning, laboratory examination and the like, the transfer condition and the in-vivo cancer cell condition of the lung cancer patients are extracted by using an N L P processing mode through deep learning algorithms such as automatic word segmentation, syntactic analysis, part of speech tagging and the like, and the detailed description is as follows:

the identification of the T stage can be deduced according to pathological reports and other reports, or can accurately recognize the position, size, volume, density, signs, doubling time and the like of the tumor mass of the primary focus by a CT chest image AI extraction technology, and accurately and automatically deduces the T stage according to the TNM definition of a corresponding version;

the identification of the N stages can be deduced according to pathological reports and other reports, or according to evidence inquiry, puncture mode examination such as mediastinoscope and the like, CT chest images, if a lymph node puncture pathological report exists, an N L P technology is used for extracting pathological report results and intelligently deducing according to extraction results, if a patient does not puncture, an intelligent 4D image system is used for extracting and intelligently deducing the condition of the farthest lymph node lesion by combining the position of a primary focus, and the N stages are accurately obtained.

The identification of the M stage can be deduced according to pathological reports and other reports, or can be extracted from other objective examination reports of the patient, such as MRI images, CT images of other parts, pathological reports (digital images) and nuclear medicine bone scans, and the M stage can be intelligently deduced according to the multi-shot and single-shot conditions of the focus.

Therefore, according to the description, the intelligent inference on the disease stage can be completed according to the T stage, the N stage and the M stage and according to the TNM definition of JACC eighth edition. For example, when a patient is admitted to a hospital for the first time, after a series of examinations are performed, the scientific research platform extracts examination information, intelligently deduces that the patient is in the stage IIA currently, and gives a deduction reason:

1. intelligently deducing two stages of T2b and N0 according to the representation of the CT chest image, wherein the position of a primary focus is defined as the upper right lobe of the lung;

2. according to the brain MRI image, the whole body bone imaging and the upper abdomen CT, the transfer condition is not found, and the M0 stage is intelligently deduced;

3. and according to the deducing results of the T stage, the N stage and the M stage, the system gives a prompt of the IIA stage.

As one solution, as shown in fig. 2, the present disclosure further provides a medical information processing system, which is linked with the medical diagnosis service data system through a corresponding data interface; wherein the processing system of the medical information comprises:

the AI identification module is configured to obtain different identification information based on different medical information, wherein the different identification information respectively comprises different pathological information;

and the analysis module is used for obtaining the interpretation information according to different identification information and standard information.

In order to process different medical information, connect a multi-service system and realize multi-mode data comprehensive treatment capacity, the processing system of the embodiment of the disclosure provides corresponding data interfaces, couples and links with different medical diagnosis service data systems, for example, couples and links with a Hospital Information System (HIS), a case history library system, a biochemical inspection data system, an institution system, a radiology department system, a pathology department system, and the like, and based on the corresponding data interfaces, data interaction with each medical diagnosis service data system can be centralized through a corresponding data protocol, so that text data (including an electronic format and a scanning format) and image data (including a medical image before identification and a medical image after identification) can be read.

Specifically, the AI identification module may include a first identification unit, a second identification unit, and a third identification unit, and respectively identifies the first medical information, the second medical information, and the third medical information, so as to obtain different identification information based on different medical information, where the different identification information respectively includes a tumor primary lesion condition, a regional lymph node affected condition, and a distant metastasis condition.

In particular, one of the inventive concepts of the present disclosure is intended to enable: obtaining first identification information based on AI identification at least on first medical information, wherein the first identification information comprises tumor primary focus conditions; obtaining second identification information based on AI identification of second medical information, wherein the second identification information comprises regional lymph node involvement; obtaining third identification information based on AI identification of third medical information, wherein the third identification information comprises a distant metastasis condition; outputting interpretation information according to the first identification information, the second identification information, the third identification information and standard information; the medical information processing system is linked with the medical diagnosis service data system through a corresponding data interface; wherein the processing system of the medical information comprises: the AI identification module is configured to obtain different identification information based on different medical information, wherein the different identification information respectively comprises different pathological information; and the analysis module is used for obtaining the interpretation information according to different identification information and standard information. Accordingly, the TNM staging intelligent inference scheme can combine text and image picture analysis. According to the scheme, by utilizing the multi-mode data comprehensive treatment capability of connecting a multi-service system and combining the medical semantic accurate interpretation capability based on the knowledge map, key information is extracted from reports and image pictures, the TNM stage is automatically deduced by using the clinical TNM stage value-taking rule, the working efficiency of doctors can be greatly improved, and the cost is reduced.

The present disclosure also provides a computer-readable storage medium having stored thereon computer-executable instructions that, when executed by a processor, primarily implement a method of processing medical information according to the above; at least comprises the following steps:

obtaining first identification information based on AI identification of first medical information, wherein the first identification information comprises the condition of a tumor primary focus;

obtaining second identification information based on AI identification of second medical information, wherein the second identification information comprises regional lymph node involvement;

obtaining third identification information based on AI identification of third medical information, wherein the third identification information comprises a distant metastasis condition;

and outputting interpretation information according to the first identification information, the second identification information, the third identification information and the standard information.

In some embodiments, a processor executing computer-executable instructions may be a processing device including one or more general purpose processing devices such as a microprocessor, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), and the like.

In some embodiments, the computer-readable storage medium may be a memory, such as a read-only memory (ROM), a random-access memory (RAM), a phase-change random-access memory (PRAM), a static random-access memory (SRAM), a dynamic random-access memory (DRAM), an electrically erasable programmable read-only memory (EEPROM), other types of random-access memory (RAM), a flash disk or other form of flash memory, a cache, a register, a static memory, a compact disc read-only memory (CD-ROM), a Digital Versatile Disc (DVD) or other optical storage, a tape cartridge or other magnetic storage device, or any other potentially non-transitory medium that may be used to store information or instructions that may be accessed by a computer device, and so forth.

In some embodiments, the computer-executable instructions may be implemented as a plurality of program modules that collectively implement the method for displaying medical images according to any one of the present disclosure.

The present disclosure describes various operations or functions that may be implemented as or defined as software code or instructions. The display unit may be implemented as software code or modules of instructions stored on a memory, which when executed by a processor may implement the respective steps and methods.

Such content may be source code or differential code ("delta" or "patch" code) that may be executed directly ("object" or "executable" form). A software implementation of the embodiments described herein may be provided through an article of manufacture having code or instructions stored thereon, or through a method of operating a communication interface to transmit data through the communication interface. A machine or computer-readable storage medium may cause a machine to perform the functions or operations described, and includes any mechanism for storing information in a form accessible by a machine (e.g., a computing display device, an electronic system, etc.), such as recordable/non-recordable media (e.g., Read Only Memory (ROM), Random Access Memory (RAM), magnetic disk storage media, optical storage media, flash memory display devices, etc.). The communication interface includes any mechanism for interfacing with any of a hardwired, wireless, optical, etc. medium to communicate with other display devices, such as a memory bus interface, a processor bus interface, an internet connection, a disk controller, etc. The communication interface may be configured by providing configuration parameters and/or transmitting signals to prepare the communication interface to provide data signals describing the software content. The communication interface may be accessed by sending one or more commands or signals to the communication interface.

The computer-executable instructions of embodiments of the present disclosure may be organized into one or more computer-executable components or modules. Aspects of the disclosure may be implemented with any number and combination of such components or modules. For example, aspects of the disclosure are not limited to the specific computer-executable instructions or the specific components or modules illustrated in the figures and described herein. Other embodiments may include different computer-executable instructions or components having more or less functionality than illustrated and described herein.

The above description is intended to be illustrative and not restrictive. For example, the above-described examples (or one or more versions thereof) may be used in combination with each other. For example, other embodiments may be used by those of ordinary skill in the art upon reading the above description. In addition, in the foregoing detailed description, various features may be grouped together to streamline the disclosure. This should not be interpreted as an intention that a disclosed feature not claimed is essential to any claim. Rather, the subject matter of the present disclosure may lie in less than all features of a particular disclosed embodiment. Thus, the following claims are hereby incorporated into the detailed description as examples or embodiments, with each claim standing on its own as a separate embodiment, and it is contemplated that these embodiments may be combined with each other in various combinations or permutations. The scope of the disclosure should be determined with reference to the appended claims, along with the full scope of equivalents to which such claims are entitled.

The above embodiments are merely exemplary embodiments of the present disclosure, which is not intended to limit the present disclosure, and the scope of the present disclosure is defined by the claims. Various modifications and equivalents of the disclosure may occur to those skilled in the art within the spirit and scope of the disclosure, and such modifications and equivalents are considered to be within the scope of the disclosure.

Claims (10)

1. The medical information processing method comprises the following steps:

obtaining first identification information based on AI identification of first medical information, wherein the first identification information comprises the condition of a tumor primary focus;

obtaining second identification information based on AI identification of second medical information, wherein the second identification information comprises regional lymph node involvement;

obtaining third identification information based on AI identification of third medical information, wherein the third identification information comprises a distant metastasis condition;

and outputting interpretation information according to the first identification information, the second identification information, the third identification information and the standard information.

2. The processing method according to claim 1, wherein the identifying based on AI of the first medical information comprises:

and extracting key text contents from the text expression, and identifying the key text contents through machine learning or deep learning.

3. The processing method according to claim 1, wherein the identifying based on AI of the first medical information comprises:

extracting primary focus from medical image, and identifying image parameter of primary focus through AI.

4. The processing method according to claim 1, wherein the identifying based on AI of the second medical information includes:

when the text expression associated with the second medical information exists, extracting key text content from the existing text expression, and identifying the key text content through machine learning or deep learning;

when there is no text expression associated with the second medical information, the farthest lymph node is extracted in the medical image in combination with the primary lesion, and the image parameters of the lymph node are identified by the AI.

5. The processing method of claim 4, wherein said extracting key text content from existing text expressions comprises:

from the lymph node puncture pathology report, a lymph node puncture pathology report result was extracted based on N L P.

6. The processing method according to claim 1, wherein the identifying based on the AI of the third medical information includes:

when the text expression associated with the third medical information exists, extracting key text contents from the existing text expression, and identifying the key text contents through machine learning or deep learning;

when there is no text expression associated with the third medical information, a lesion is extracted in the medical image, and a multiple and/or single occurrence of the lesion is identified by the AI.

7. The processing method according to claim 6,

extracting key text content from existing text presentation, including extracting text description content of the focus from diagnosis reports of other parts based on N L P;

the step of extracting the focus in the medical image comprises the step of extracting the focus from medical images of other parts, wherein the medical images of other parts comprise MRI images, CT images and nuclear medicine bone scanning images.

8. The processing method according to any one of claims 1 to 7, wherein the outputting interpretation information based on the first identification information, the second identification information, the third identification information, and standard information includes:

and outputting interpretation information about the lung cancer by taking the TNM staging standard as standard information.

9. The medical information processing system is linked with the medical diagnosis service data system through a corresponding data interface; wherein the processing system of the medical information comprises:

the AI identification module is configured to obtain different identification information based on different medical information, wherein the different identification information respectively comprises different pathological information;

and the analysis module is used for obtaining the interpretation information according to different identification information and standard information.

10. A computer-readable storage medium having stored thereon computer-executable instructions that, when executed by a processor, implement:

the treatment method according to any one of claims 1 to 8.

Images